The present invention relates to an improved method of providing identification of a user or authentication of a user's identity. More particularly, the present invention relates to an improved method of providing identification of a user or authentication of a user's identity using conditional behavioural biometrics.
For the purposes of this specification, identification typically involves the collection of data and a determination of who a user is from a database of users while authentication typically involves the use of data to confirm a user is who they present themselves to be (i.e. to verify a user's identity).
Identification and/or authentication of a user identity is an essential step in accessing many secure services or devices, such as banking, stored personal details or other restricted data. This identification and/or authentication is usually achieved by the use of passwords or personal identification numbers (PINs), which are usually assumed to be known only by the authorised user or users of a service or device.
However, knowledge of a user's password or PIN is enough for an unauthorised third party to gain access to the service or device. Additional layers of security or improved security are therefore required to reduce the risk of passwords and PINs from being used by unauthorised third parties.
Adding further security measures to the authentication process usually requires a trade-off between the increased level of security and the degradation of the user experience.
The present invention seeks to provide an enhanced method of authenticating and/or identifying a user identity using conditional behavioural biometrics.
According to a first aspect of the present invention, there is provided a method of generating a user profile for use in identifying and/or authenticating a user on a device, the device equipped with one or more sensors, the method comprising: generating a set of data points from sensory data collected by the one or more sensors; clustering the set of data points to produce a set of data clusters; developing a first classifier for the data clusters, the first classifier being operable to assign a further data point derived from a further user interaction with the computing device to one of the data clusters; and developing one or more further classifiers for at least one of the data clusters, the further classifier operable to identify and/or authenticate a user identity based on the further data point.
According to a second aspect of the invention, there is provided a method of identifying and/or authenticating a user on a device, the device equipped with one or more sensors, the method comprising: generating a data point from sensory data derived from a user interaction with the device; assigning the data point to a cluster of data points using a first classifier, the first classifier developed from a plurality of previous user interactions with the device; and applying a second classifier to the data point, the second classifier being chosen based on the assigned data cluster, and operable to identify and/or authenticate a user identity based on the further data point.
By classifying sensory data based on previous user interactions with a computing device, an additional layer of security can be provided over solely using a password or PIN input for security as a device can identify and/or authenticate a user separately to the user providing credentials to identify or authenticate themselves (or identify then authenticate themselves). The classifier is developed from a plurality of previous user interactions with the computing device. Using conditional behavioural biometrics can remove the trade-off between security versus any degradation of the user experience necessary when using PINs or passwords to authenticate a user. Optionally, the classifier can be based on biometric and/or behavioural data collected, further optionally where the classifier can be based on biometric and/or behavioural data collected during a user interaction with the device. By clustering user data while generating a user profile, different user contexts can be identified and a separate identification and/or authentication classifier can be trained for each one. Having context specific classifiers for identification and/or authentication can allow for a higher accuracy of identification and/or authentication in comparison with using a single classifier for every situation, since a user will in general interact with a computing device differently depending on the context. Herein, sensory data is used to connote data from or derived from the sensors—i.e. sensor data. A classifier is taken to connote any algorithm for statistical classification of a data set.
Optionally, the sensory data is collected during a plurality of user interactions with the device.
By using the data collected during multiple user interactions with the device to develop the user profile a more accurate set of classifiers may be obtained.
Optionally, an algorithm is used to perform the clustering of the data points derived from the sensory data.
Optionally, the algorithm is one or more clustering algorithms based on one of a K-means algorithm or a Gaussian Mixture Model using an Expectation-Maximisation algorithm.
K-means algorithms and Gaussian Mixture Models can be used to efficiently cluster the user data during the generation of a user profile.
Optionally, the identification and/or authentication of the user further comprises the step of identifying and/or authenticating the user identity using the further classifiers.
Using the classifiers to identify and/or authenticate the user identity can remove the need for the user to manually enter identification and/or authentication data, enhancing the user experience.
Optionally, the output of the second classifier is a confidence score in the user identity and/or authentication.
Optionally, if the confidence score is below a pre-defined threshold, further identification and/or authentication steps are carried out or the user is not identified and/or authenticated.
By providing a confidence score and using it to determine if further identification and/or authentication steps are required, the error rate associated with false negatives can be reduced.
Optionally, the computing device comprises at least one of: a mobile device; a local server; a cloud or network based server; and a desktop computer.
The profile generation and identification/authentication methods can be performed locally on the user device, remotely on a server or on a combination of the two. This allows for greater flexibility in the implementation of the method.
Embodiments of the present invention will now be described, by way of example only and with reference to the accompanying drawings having like-reference numerals, in which:
Referring to
The method relates to providing enhanced identification and/or authentication of the identity of a user on a computing device, by using the user's behaviour while interacting with the device. The method is principally divided into two steps: (a) generating a user profile (herein referred to as the “enrolment stage”) based on data collected by the device, optionally only while a user is interacting with the device and further optionally when the user is inputting passwords, PINs or any identity of security data; and (b) the authentication stage, wherein the user profile generated in the enrolment stage is used to authenticate a user identity based on behavioural data collected while inputting a password, PIN or any identity or security data.
Referring to
The object of the enrolment stage of the method is to generate a user profile from data generated during a user's interactions with a computing device. The user profile comprises a set of K data clusters corresponding to different contexts to the user activity, a classifier C for assigning new data points to clusters, and a further classifier Ck associated with each cluster for determining whether a user is authentic or not from sensory data collected while the user is entering their details.
The user activity contexts include, but are not limited to, the user location, the user activity (for example the user's movement speed or whether the user is listening to music), the computing device's connections or the device orientation (for example, if the computing device is a mobile device, whether it is the portrait or landscape orientation).
The use of different classifiers for authenticating the user, taking into account the context, allows for a higher degree of accuracy in authenticating the user identity than the use of a single classifier for all situations. For example, a user interacting with a device held in their hand while walking will interact with the device differently to a device on a table in front of them while sitting. The orientation of the device (i.e. whether it is in portrait or landscape modes) may also affect how the user interacts with the device.
During use, a user can interact with a computing device to input, for example, a password or PIN for accessing a secure service or the device. The computing device may be, for example, a personal computer (such as a desktop or laptop computer), mobile computing device (such as a mobile telephone or tablet) or a fixed terminal (such as an ATM or touchscreen kiosk). The computing device is equipped with one or more sensors for measuring certain properties of the user's interaction with the device, and/or environmental properties during the interaction and/or in the background during normal use of the device. The data derived directly from the device sensors will herein be referred to as raw sensory data.
For example, if interacting with a touchscreen device, the touch time, touch timing, touch pressure, touch area and touch location coordinates can be detected and recorded. Other non-limiting examples of raw sensory data include accelerometer data, gyroscopic data, GPS co-ordinates and hover co-ordinates.
Raw sensory data need not only be collected when the user is consciously interacting with the device. For example, if the device is a mobile device, then raw sensory data may be collected while the device is in the user's pocket to provide information about, for example, the user's walking style or how they sit or stand. As raw sensory data can be collected continuously by the device (whether during operation by the user or not), the monitoring of the user's sensory data is continuous and invisible to user, thus the verification of the identity of the user can similarly be continuous and invisible to the user. In contrast, the use of a PIN or fingerprints can only verify identity at a point in time.
The raw sensory data associated with the user's interaction with the device is then passed to a pre-processor (or processor), where it is converted into derived sensory data. Derived sensory data comprises a set of features that can be calculated or derived from the raw sensory data, but which features may not be determined directly by the device's sensors. Non-sensory data derived from other sources (such as the internet) may also be combined with the raw sensory data to generate derived sensory data or used as raw sensory data, depending on the implementation details of the method.
Features derived from raw sensory data can include: a duration of touchscreen interaction; a physical touchscreen interaction distance; a time between touchscreen interactions; maximum, minimum and/or average deviation from a straight line during a touchscreen interaction; acceleration and/or deceleration of a touchscreen interaction; curvature of a touchscreen interaction; length of a touchscreen interaction (all derived from touchscreen associated data); background tremor while using the device; tremor during the interaction with the device (both derived from accelerometer and gyroscope data); device (and therefore user) movement speed (derived from device GPS coordinates and/or other device location service or services); and the orientation of the computing device (derived from magnetometer data). Many other example features are possible to derive from the raw sensory data.
This derived sensory data, along with any usable raw sensory data, is used to generate a data point associated with that particular user interaction. The data point is then added to a user data set, comprising all the data points associated with a given user. If the total number of data points in the set after the new point has been added is fewer than a predetermined number, N, then the process is repeated for further user interactions until the predetermined number of data points has been reached. This data set will form a training set of data for training classifiers for use in authenticating the user identity. It can be stored locally on the user's device and/or in a back end server associated with the provider of the secure service.
The data point comprises a subset of all the raw and derived sensory data. For example, it may include x and y touch coordinates, pressure, typing speed, touch durations and geolocation. Many other examples are possible.
Once the size of the data set has reached a predefined number of data points, a clustering or classification algorithm (herein referred to as algorithm A) is applied to the user data set. The predefined number of data points can be predetermined to be statistically significant or sufficient to allow the classification algorithm to be able to substantially reliably identify the user, or can be chosen adaptively using machine learning techniques. Algorithm A takes the user data set as an input and produces a model of a set of K clusters or classes corresponding to different user behaviours based on a subset of the user data. The subset of data used is predetermined, but alternatively may again be chosen adaptively using machine learning techniques. The optimal number of classes can be chosen using cross validation.
An example of the type of algorithm used as Algorithm A is a K-means clustering algorithm. In this example, initially a set of K random “mean” points is generated. Each of the data points in the data set are assigned to the nearest one of these mean points, based on a metric (for example the Euclidean distance), to form a set of K clusters. A new mean point for each of these clusters is then calculated. The points in the data set are then reassigned to the nearest of these new means to form K new clusters. These two steps are repeated until convergence (in the sense that the clusters no longer change or substantially change between iterations) is achieved. Many other examples are possible, such as Gaussian Mixture Models using an Expectation-Maximisation algorithm.
The clusters identified in this way should correspond to different user activity contexts.
Algorithm A also uses the user data set to develop a classifier C, which can be used to identify further data points as associated with one of the K clusters. This classifier may, for example, be based on a K-nearest neighbour classification, details of which will be outlined below.
Once the data clusters corresponding to different user environments or behaviours have been determined by algorithm A, a second classification algorithm (herein referred to as algorithm B) is applied to the data points within each cluster Ki. Algorithm B trains a separate classifier Ci for each of the K clusters, which distinguishes between a legitimate user and an illegitimate one (an “attacker”). Algorithm B is based on a Random Forest decision-learning tree, but other examples are possible.
It should be noted that algorithm B could be a set of algorithms, for each of the different K clusters.
The output of the enrolment stage is therefore multiple classifiers, or a classifier and a classifier set: a first classifier C for assigning new data points to one of the K clusters identified by algorithm A; and a set of further classifiers {Ci}, each of which is associated with one of the data clusters and is operable to provide authentication of a new data point.
The first classifier and the second classifier set, along with the derived sensory data used to train them, may be stored on the user's computing device, or alternatively on a remote server or group of servers (e.g. a cloud service or cloud) that could, for example, be under the control of the secure service provider. Likewise, the identification of the K clusters and the training of the classifiers can take place either on the user's computing device, or remotely (e.g. within the cloud).
Referring now to
In the authentication stage of the method, a user interacts with the computing device, generating a data point from sensory data, which is used to authenticate the user's identity.
The authentication stage begins with the user interacting with the computing device while entering authentication data, such as a password or PIN. As the authentication data is entered, raw sensory data, as described above, is generated by sensors associated with the computing device. A pre-processor (or processor) then converts this raw sensory data to derived sensory data, as described above, and generates a data point from it. In this regard, the first steps of the authentication stage are substantially identical to those of the enrolment stage.
Upon generation of the data point, the classifier C (generated by algorithm A in the enrolment stage) is applied to it. This determines which of the K clusters, identified by algorithm A, the data point should be associated with, i.e. which user situation and/or behaviour is the most appropriate to use given the sensory inputs. This can be, for example, achieved by the use of a K-nearest neighbour algorithm, which works by determining the class of the K (not to be confused with the number of clusters) nearest points in the dataset, based on a distance metric (for example the Euclidean distance), and assigning the data point to a cluster based on which cluster contains the largest number of nearest points. It will be appreciated that alternatives to a K-nearest neighbour approach may be used.
Once the first classifier has identified the appropriate cluster, Ki, the corresponding second classifier, Ci, developed by algorithm B in the enrolment stage and associated with the identified cluster, is applied to the data point. This second stage classifier is based on a random forest algorithm, in which the data point is passed through the ensemble of decision trees trained during the enrolment stage. The output of each of these trees is either a pass or a fail. The ratio of the number of passes to the number of fails is used to determine a confidence score that the user identity is correct. The classifier may alternatively be based on a number of other algorithms, including, but not limited to: neural networks; k-nearest neighbours; and naïve Bayes.
The output of the second classifier is a confidence score for the user being an approved user. If this score is above a pre-determined threshold, the user is authenticated as a legitimate, authorised user. The threshold is variable depending on the requirements of the service being accessed by the user, and can be set to prioritise minimising false-positives or false negatives. It adjusts automatically based on the data used to train the classifiers in order to achieve the desired error rates.
The confidence score is output along with the pass/fail authentication result.
If the confidence score does exceed the required threshold, the user may be asked to input more security or authentication data—for example, answering security questions or inputting passwords or PINs.
In an alternative embodiment, the user's interaction with the device is used as described above to authenticate the user identity, without the user being required to input any security data. The user sensory data is collected and monitored in the background on the device and, when a user would normally be required to login to a service to perform authentication, as long as the behavioural biometrics continues to classify the user as the authorised user the user will not be required to provide any password, PIN or fingerprint (for example during an online check out process when purchasing goods or services over the Internet) as any authentication is performed in the background. Should the behavioural biometrics fail to continue to classify the user as the authorised user, the user will be asked to enter further security information.
A user may interact with a secure service through multiple different devices or types of device. When this is the case, the total user data sets associated with the user will be partitioned into subsets based on the device identity before algorithm A is applied. Enrolment is essentially performed for each device type individually.
The computations associated with the enrolment and authentication stages (i.e. the application of algorithms A and B in enrolment and of the classifiers in authentication) can be performed either on the user computing device itself, or on a server or servers associated with the provider of the secure service, or in combination between the device and server or servers.
There are four examples presented here:
In the first example, all computation is performed on the server. The raw and/or derived sensory data derived from the computing device's sensors is transmitted to the server across a network, where the algorithms or classifiers are applied to it. The classifiers trained in the enrolment stage are stored on the server.
In the second example, all the computations are performed on the user device. The classifiers are stored locally on the user computing device. An authentication message is sent to the server upon the computing device authenticating the user identity, allowing the user access to the secure service.
The third example splits the computation between the server and the computer. The enrolment stage computations are performed on the server to train the classifiers. These are then transmitted to the user computing device and stored locally. The user computing device applies the classifiers to the user data point being used for authentication and transmits a message to the server indicating success or failure. This combination is advantageous in the cases when the user computing device has limited processing power, or when the data set is very large.
The fourth example performs the enrolment stage calculations on the user computing device and then transmits the trained classifiers to the server. The authentication stage calculations are then performed by the server when it receives sensory data (or a data point) transmitted to it across a network by the computing device.
If the user is authenticated then the newly authenticated data point can be added to the set data points for use in a future enrolment stage update. Every time a pre-defined number of new data points, M, are added to the data set the model generated by the enrolment stage is updated. This can be done continuously by using the current models as a starting point, or the models can be regenerated completely.
Any system feature as described herein may also be provided as a method feature, and vice versa. As used herein, means plus function features may be expressed alternatively in terms of their corresponding structure.
Any feature in one aspect of the invention may be applied to other aspects of the invention, in any appropriate combination. In particular, method aspects may be applied to system aspects, and vice versa. Furthermore, any, some and/or all features in one aspect can be applied to any, some and/or all features in any other aspect, in any appropriate combination.
It should also be appreciated that particular combinations of the various features described and defined in any aspects of the invention can be implemented and/or supplied and/or used independently.
Number | Date | Country | Kind |
---|---|---|---|
1511230 | Jun 2015 | GB | national |
This patent application is a Continuation of U.S. Ser. No. 15/192,845, filed on Jun. 24, 2016, which is hereby incorporated by reference in its entirety; which claims priority from Great Britain Patent Application GB 1511230.3, filed on Jun. 25, 2015, which is hereby incorporated by reference in its entirety.
Number | Name | Date | Kind |
---|---|---|---|
3618019 | Nemirovsky | Nov 1971 | A |
3699517 | Dyche | Oct 1972 | A |
3983535 | Herbst | Sep 1976 | A |
4128829 | Herbst | Dec 1978 | A |
4621334 | Garcia | Nov 1986 | A |
4760386 | Heath | Jul 1988 | A |
4805222 | Young | Feb 1989 | A |
5305238 | Starr | Apr 1994 | A |
5442342 | Kung | Aug 1995 | A |
5485171 | Copper | Jan 1996 | A |
5557686 | Brown | Sep 1996 | A |
5565657 | Merz | Oct 1996 | A |
5581261 | Hickman | Dec 1996 | A |
5838306 | O'Connor | Nov 1998 | A |
5874941 | Yamada | Feb 1999 | A |
5999162 | Takahashi | Dec 1999 | A |
6202023 | Hancock | Mar 2001 | B1 |
6337686 | Wong | Jan 2002 | B2 |
6337919 | Dunton | Jan 2002 | B1 |
6442692 | Zilberman | Aug 2002 | B1 |
6572014 | Lambert | Jun 2003 | B1 |
6819219 | Bolle | Nov 2004 | B1 |
6836554 | Bolle | Dec 2004 | B1 |
6895514 | Kermani | May 2005 | B1 |
6931131 | Becker | Aug 2005 | B1 |
6938061 | Rumynin | Aug 2005 | B1 |
6938159 | O'Connor | Aug 2005 | B1 |
6957185 | Labaton | Oct 2005 | B1 |
6957186 | Guheen | Oct 2005 | B1 |
6983061 | Ikegami | Jan 2006 | B2 |
7092926 | Cerrato | Aug 2006 | B2 |
7130452 | Bolle | Oct 2006 | B2 |
7133792 | Murakami | Nov 2006 | B2 |
7139916 | Billingsley | Nov 2006 | B2 |
7158118 | Liberty | Jan 2007 | B2 |
7236156 | Liberty | Jun 2007 | B2 |
7245218 | Ikehara | Jul 2007 | B2 |
7366919 | Sobel | Apr 2008 | B1 |
7395436 | Nemovicher | Jul 2008 | B1 |
7494061 | Reinhold | Feb 2009 | B2 |
7523191 | Thomas | Apr 2009 | B1 |
7535456 | Liberty | May 2009 | B2 |
7606915 | Calinov | Oct 2009 | B1 |
7796013 | Murakami | Sep 2010 | B2 |
7818290 | Davis | Oct 2010 | B2 |
7860870 | Sadagopan | Dec 2010 | B2 |
8031175 | Rigazio | Oct 2011 | B2 |
8065624 | Morin | Nov 2011 | B2 |
8125312 | Orr | Feb 2012 | B2 |
8156324 | Shnowske | Apr 2012 | B1 |
8170953 | Tullis | May 2012 | B1 |
8171085 | Tevanian, Jr. | May 2012 | B1 |
8201222 | Inoue | Jun 2012 | B2 |
8244211 | Clark | Aug 2012 | B2 |
8285658 | Kellas-Dicks | Oct 2012 | B1 |
8417960 | Takahashi | Apr 2013 | B2 |
8433785 | Awadallah | Apr 2013 | B2 |
8449393 | Sobel | May 2013 | B2 |
8499245 | Froment | Jul 2013 | B1 |
8510113 | Conkie | Aug 2013 | B1 |
8548208 | Schultz | Oct 2013 | B2 |
8549629 | Mccreesh | Oct 2013 | B1 |
8555077 | Davis | Oct 2013 | B2 |
8621209 | Johansson | Dec 2013 | B1 |
8745729 | Poluri | Jun 2014 | B2 |
8788838 | Fadell | Aug 2014 | B1 |
8803797 | Scott | Aug 2014 | B2 |
8819812 | Weber | Aug 2014 | B1 |
8832823 | Boss | Sep 2014 | B2 |
8838060 | Walley | Sep 2014 | B2 |
8880441 | Chen | Nov 2014 | B1 |
8898787 | Thompson | Nov 2014 | B2 |
8904479 | Johansson | Dec 2014 | B1 |
8938787 | Turgeman | Jan 2015 | B2 |
8941466 | Bayram | Jan 2015 | B2 |
8990959 | Zhu | Mar 2015 | B2 |
9069942 | Turgeman | Jun 2015 | B2 |
9071969 | Turgeman | Jun 2015 | B2 |
9154534 | Gayles | Oct 2015 | B1 |
9174123 | Nasiri | Nov 2015 | B2 |
9195351 | Rosenberg | Nov 2015 | B1 |
9203860 | Casillas | Dec 2015 | B1 |
9275337 | Turgeman | Mar 2016 | B2 |
9282112 | Filatov | Mar 2016 | B2 |
9301140 | Costigan | Mar 2016 | B1 |
9304915 | Adams | Apr 2016 | B2 |
9355231 | Disraeli | May 2016 | B2 |
9355234 | Magi Shaashua | May 2016 | B1 |
9418221 | Turgeman | Aug 2016 | B2 |
9430629 | Ziraknejad | Aug 2016 | B1 |
9450971 | Turgeman | Sep 2016 | B2 |
9477826 | Turgeman | Oct 2016 | B2 |
9483292 | Turgeman | Nov 2016 | B2 |
9526006 | Turgeman | Dec 2016 | B2 |
9529987 | Deutschmann | Dec 2016 | B2 |
9531701 | Turgeman | Dec 2016 | B2 |
9531733 | Turgeman | Dec 2016 | B2 |
9536071 | Turgeman | Jan 2017 | B2 |
9541995 | Turgeman | Jan 2017 | B2 |
9547766 | Turgeman | Jan 2017 | B2 |
9552470 | Turgeman | Jan 2017 | B2 |
9558339 | Turgeman | Jan 2017 | B2 |
9589120 | Samuel | Mar 2017 | B2 |
9621567 | Turgeman | Apr 2017 | B2 |
9626677 | Turgeman | Apr 2017 | B2 |
9654485 | Neumann | May 2017 | B1 |
9665703 | Turgeman | May 2017 | B2 |
9674218 | Turgeman | Jun 2017 | B2 |
9690915 | Turgeman | Jun 2017 | B2 |
9703953 | Turgeman | Jul 2017 | B2 |
9710316 | Chheda | Jul 2017 | B1 |
9712558 | Turgeman | Jul 2017 | B2 |
9747436 | Turgeman | Aug 2017 | B2 |
9779423 | Turgeman | Oct 2017 | B2 |
9832192 | Alonso Cebrian | Nov 2017 | B2 |
9838373 | Turgeman | Dec 2017 | B2 |
9848009 | Turgeman | Dec 2017 | B2 |
9927883 | Lin | Mar 2018 | B1 |
10032010 | Turgeman | Jul 2018 | B2 |
10037421 | Turgeman | Jul 2018 | B2 |
10049209 | Turgeman | Aug 2018 | B2 |
10055560 | Turgeman | Aug 2018 | B2 |
10069837 | Turgeman | Sep 2018 | B2 |
10069852 | Turgeman | Sep 2018 | B2 |
10079853 | Turgeman | Sep 2018 | B2 |
10083439 | Turgeman | Sep 2018 | B2 |
10164985 | Turgeman | Dec 2018 | B2 |
10198122 | Turgeman | Feb 2019 | B2 |
10262324 | Turgeman | Apr 2019 | B2 |
10298614 | Turgeman | May 2019 | B2 |
10395018 | Turgeman | Aug 2019 | B2 |
10397262 | Karabchevsky | Aug 2019 | B2 |
10404729 | Turgeman | Sep 2019 | B2 |
10474815 | Turgeman | Nov 2019 | B2 |
10476873 | Turgeman | Nov 2019 | B2 |
10523680 | Turgeman | Dec 2019 | B2 |
10579784 | Turgeman | Mar 2020 | B2 |
10586036 | Turgeman | Mar 2020 | B2 |
10621585 | Turgeman | Apr 2020 | B2 |
10685355 | Novick | Jun 2020 | B2 |
10719765 | Novik | Jul 2020 | B2 |
10728761 | Kedem | Jul 2020 | B2 |
20010004733 | Eldering | Jun 2001 | A1 |
20020023229 | Hangai | Feb 2002 | A1 |
20020089412 | Heger | Jul 2002 | A1 |
20030033526 | French | Feb 2003 | A1 |
20030074201 | Grashey | Apr 2003 | A1 |
20030137494 | Tulbert | Jul 2003 | A1 |
20030149803 | Wilson | Aug 2003 | A1 |
20030212811 | Thornton | Nov 2003 | A1 |
20040015714 | Abraham | Jan 2004 | A1 |
20040017355 | Shim | Jan 2004 | A1 |
20040021643 | Hoshino | Feb 2004 | A1 |
20040034784 | Fedronic | Feb 2004 | A1 |
20040062423 | Doi | Apr 2004 | A1 |
20040111523 | Hall | Jun 2004 | A1 |
20040123156 | Hammond | Jun 2004 | A1 |
20040128240 | Yusin | Jul 2004 | A1 |
20040143737 | Teicher | Jul 2004 | A1 |
20040186882 | Ting | Sep 2004 | A1 |
20040221171 | Ahmed | Nov 2004 | A1 |
20050008148 | Jacobson | Jan 2005 | A1 |
20050060138 | Wang | Mar 2005 | A1 |
20050179657 | Russo | Aug 2005 | A1 |
20050289264 | Illowsky | Dec 2005 | A1 |
20060006803 | Huang | Jan 2006 | A1 |
20060080263 | Willis | Apr 2006 | A1 |
20060090073 | Steinberg | Apr 2006 | A1 |
20060123101 | Buccella | Jun 2006 | A1 |
20060143454 | Walmsley | Jun 2006 | A1 |
20060195328 | Abraham | Aug 2006 | A1 |
20060215886 | Black | Sep 2006 | A1 |
20060224898 | Ahmed | Oct 2006 | A1 |
20060238490 | Stanley | Oct 2006 | A1 |
20060239430 | Gue | Oct 2006 | A1 |
20060280339 | Cho | Dec 2006 | A1 |
20060282660 | Varghese | Dec 2006 | A1 |
20060284969 | Kim | Dec 2006 | A1 |
20070118804 | Raciborski | May 2007 | A1 |
20070156443 | Gurvey | Jul 2007 | A1 |
20070174082 | Singh | Jul 2007 | A1 |
20070183633 | Hoffmann | Aug 2007 | A1 |
20070214426 | Ruelle | Sep 2007 | A1 |
20070226797 | Thompson | Sep 2007 | A1 |
20070236330 | Cho | Oct 2007 | A1 |
20070240230 | O'Connell | Oct 2007 | A1 |
20070241861 | Venkatanna | Oct 2007 | A1 |
20070250920 | Lindsay | Oct 2007 | A1 |
20070255821 | Ge | Nov 2007 | A1 |
20070266305 | Cong | Nov 2007 | A1 |
20070271466 | Mak | Nov 2007 | A1 |
20070283416 | Renaud | Dec 2007 | A1 |
20080046982 | Parkinson | Feb 2008 | A1 |
20080059474 | Lim | Mar 2008 | A1 |
20080068343 | Hoshino | Mar 2008 | A1 |
20080084972 | Burke | Apr 2008 | A1 |
20080091453 | Meehan | Apr 2008 | A1 |
20080091639 | Davis | Apr 2008 | A1 |
20080092209 | Davis | Apr 2008 | A1 |
20080092245 | Alward | Apr 2008 | A1 |
20080097851 | Bemmel | Apr 2008 | A1 |
20080098456 | Alward | Apr 2008 | A1 |
20080120717 | Shakkarwar | May 2008 | A1 |
20080136790 | Hio | Jun 2008 | A1 |
20080162449 | Chao-Yu | Jul 2008 | A1 |
20080183745 | Cancel | Jul 2008 | A1 |
20080192005 | Elgoyhen | Aug 2008 | A1 |
20080200310 | Tagliabue | Aug 2008 | A1 |
20080211766 | Westerman | Sep 2008 | A1 |
20080215576 | Zhao | Sep 2008 | A1 |
20080263636 | Gusler | Oct 2008 | A1 |
20080298588 | Shakkarwar | Dec 2008 | A1 |
20080301808 | Calo | Dec 2008 | A1 |
20080306897 | Liu | Dec 2008 | A1 |
20080309616 | Massengill | Dec 2008 | A1 |
20090037983 | Chiruvolu | Feb 2009 | A1 |
20090038010 | Ma | Feb 2009 | A1 |
20090049555 | Cho | Feb 2009 | A1 |
20090089879 | Wang | Apr 2009 | A1 |
20090094311 | Awadallah | Apr 2009 | A1 |
20090132395 | Lam | May 2009 | A1 |
20090133106 | Bentley | May 2009 | A1 |
20090134972 | Wu, Jr. | May 2009 | A1 |
20090157792 | Fiatal | Jun 2009 | A1 |
20090172551 | Kane | Jul 2009 | A1 |
20090189736 | Hayashi | Jul 2009 | A1 |
20090199296 | Xie | Aug 2009 | A1 |
20090203355 | Clark | Aug 2009 | A1 |
20090227232 | Matas | Sep 2009 | A1 |
20090241188 | Komura | Sep 2009 | A1 |
20090254336 | Dumais | Oct 2009 | A1 |
20090281979 | Tysowski | Nov 2009 | A1 |
20090293119 | Jonsson | Nov 2009 | A1 |
20090300589 | Watters | Dec 2009 | A1 |
20090303204 | Nasiri | Dec 2009 | A1 |
20090320123 | Yu | Dec 2009 | A1 |
20100007632 | Yamazaki | Jan 2010 | A1 |
20100040293 | Hermann | Feb 2010 | A1 |
20100042387 | Gibbon | Feb 2010 | A1 |
20100042403 | Chandrasekar | Feb 2010 | A1 |
20100046806 | Baughman | Feb 2010 | A1 |
20100070405 | Joa | Mar 2010 | A1 |
20100077470 | Kozat | Mar 2010 | A1 |
20100082747 | Yue | Apr 2010 | A1 |
20100082998 | Kohavi | Apr 2010 | A1 |
20100097324 | Anson | Apr 2010 | A1 |
20100115610 | Tredoux | May 2010 | A1 |
20100122082 | Deng | May 2010 | A1 |
20100125816 | Bezos | May 2010 | A1 |
20100138370 | Wu | Jun 2010 | A1 |
20100164897 | Morin | Jul 2010 | A1 |
20100171753 | Kwon | Jul 2010 | A1 |
20100197352 | Runstedler | Aug 2010 | A1 |
20100203876 | Krishnaswamy | Aug 2010 | A1 |
20100225443 | Bayram | Sep 2010 | A1 |
20100245553 | Schuler | Sep 2010 | A1 |
20100269165 | Chen | Oct 2010 | A1 |
20100281539 | Bums | Nov 2010 | A1 |
20100284532 | Burnett | Nov 2010 | A1 |
20100287229 | Hauser | Nov 2010 | A1 |
20100321304 | Rofougaran | Dec 2010 | A1 |
20100328074 | Johnson | Dec 2010 | A1 |
20110010209 | McNally | Jan 2011 | A1 |
20110012829 | Yao | Jan 2011 | A1 |
20110016320 | Bergsten | Jan 2011 | A1 |
20110016534 | Jakobsson | Jan 2011 | A1 |
20110018828 | Wu | Jan 2011 | A1 |
20110023115 | Wright | Jan 2011 | A1 |
20110029902 | Bailey | Feb 2011 | A1 |
20110039529 | Kim | Feb 2011 | A1 |
20110039602 | McNamara | Feb 2011 | A1 |
20110043475 | Rigazio | Feb 2011 | A1 |
20110050394 | Zhang | Mar 2011 | A1 |
20110055077 | French | Mar 2011 | A1 |
20110063211 | Hoerl | Mar 2011 | A1 |
20110065504 | Dugan | Mar 2011 | A1 |
20110066682 | Aldunate | Mar 2011 | A1 |
20110082768 | Eisen | Apr 2011 | A1 |
20110102570 | Wilf | May 2011 | A1 |
20110105103 | Ullrich | May 2011 | A1 |
20110105859 | Popovic | May 2011 | A1 |
20110113388 | Eisen | May 2011 | A1 |
20110154273 | Aburada | Jun 2011 | A1 |
20110154497 | Bailey | Jun 2011 | A1 |
20110159650 | Shiraishi | Jun 2011 | A1 |
20110159850 | Faith | Jun 2011 | A1 |
20110162076 | Song | Jun 2011 | A1 |
20110191820 | Ivey | Aug 2011 | A1 |
20110193737 | Chiueh | Aug 2011 | A1 |
20110202453 | Issa | Aug 2011 | A1 |
20110221684 | Rydenhag | Sep 2011 | A1 |
20110223888 | Esaki | Sep 2011 | A1 |
20110225644 | Pullikottil | Sep 2011 | A1 |
20110246902 | Tsai | Oct 2011 | A1 |
20110248941 | Abdo | Oct 2011 | A1 |
20110251823 | Davis | Oct 2011 | A1 |
20110271342 | Chung | Nov 2011 | A1 |
20110276414 | Subbarao | Nov 2011 | A1 |
20110286730 | Gallagher | Nov 2011 | A1 |
20110300831 | Chin | Dec 2011 | A1 |
20110304531 | Brooks | Dec 2011 | A1 |
20110320822 | Lind | Dec 2011 | A1 |
20120005483 | Patvarczki | Jan 2012 | A1 |
20120005719 | McDougal | Jan 2012 | A1 |
20120007821 | Zaliva | Jan 2012 | A1 |
20120054834 | King | Mar 2012 | A1 |
20120096555 | Mahaffey | Apr 2012 | A1 |
20120102551 | Bidare | Apr 2012 | A1 |
20120113061 | Ikeda | May 2012 | A1 |
20120123932 | LeCuyer | May 2012 | A1 |
20120124662 | Baca | May 2012 | A1 |
20120133055 | Machida | May 2012 | A1 |
20120151559 | Koudys | Jun 2012 | A1 |
20120154173 | Chang | Jun 2012 | A1 |
20120154273 | McDade | Jun 2012 | A1 |
20120154823 | Sakamoto | Jun 2012 | A1 |
20120158503 | Mardikar | Jun 2012 | A1 |
20120159599 | Szoke | Jun 2012 | A1 |
20120164978 | Conti | Jun 2012 | A1 |
20120167170 | Shi | Jun 2012 | A1 |
20120167204 | Akka | Jun 2012 | A1 |
20120174213 | Geiger | Jul 2012 | A1 |
20120188198 | Jeong | Jul 2012 | A1 |
20120204257 | O'Connell | Aug 2012 | A1 |
20120218193 | Weber | Aug 2012 | A1 |
20120239557 | Weinflash | Sep 2012 | A1 |
20120246737 | Paxton | Sep 2012 | A1 |
20120252410 | Williams | Oct 2012 | A1 |
20120278804 | Narayanasamy | Nov 2012 | A1 |
20120284380 | Anderson | Nov 2012 | A1 |
20120297476 | Zeljkovic | Nov 2012 | A1 |
20130018796 | Kolhatkar | Jan 2013 | A1 |
20130024239 | Baker | Jan 2013 | A1 |
20130036416 | Raju | Feb 2013 | A1 |
20130061169 | Pearcy | Mar 2013 | A1 |
20130076650 | Vik | Mar 2013 | A1 |
20130088434 | Masuda | Apr 2013 | A1 |
20130097682 | Zeljkovic | Apr 2013 | A1 |
20130097706 | Titonis | Apr 2013 | A1 |
20130109944 | Sparacino | May 2013 | A1 |
20130111586 | Jackson | May 2013 | A1 |
20130132091 | Skerpac | May 2013 | A1 |
20130133055 | Ali | May 2013 | A1 |
20130135218 | Jain | May 2013 | A1 |
20130139248 | Rhee | May 2013 | A1 |
20130154999 | Guard | Jun 2013 | A1 |
20130162603 | Peng | Jun 2013 | A1 |
20130167212 | Azar | Jun 2013 | A1 |
20130198832 | Draluk | Aug 2013 | A1 |
20130212674 | Boger | Aug 2013 | A1 |
20130237272 | Prasad | Sep 2013 | A1 |
20130239195 | Turgeman | Sep 2013 | A1 |
20130239206 | Draluk | Sep 2013 | A1 |
20130243208 | Fawer | Sep 2013 | A1 |
20130254642 | Seo | Sep 2013 | A1 |
20130282637 | Costigan | Oct 2013 | A1 |
20130288647 | Turgeman | Oct 2013 | A1 |
20130305357 | Ayyagari | Nov 2013 | A1 |
20130312097 | Turnbull | Nov 2013 | A1 |
20130335349 | Ferren | Dec 2013 | A1 |
20130346309 | Giori | Dec 2013 | A1 |
20140033317 | Barber | Jan 2014 | A1 |
20140041020 | Zhao | Feb 2014 | A1 |
20140078061 | Simons | Mar 2014 | A1 |
20140078193 | Bamhoefer | Mar 2014 | A1 |
20140082369 | Waclawsky | Mar 2014 | A1 |
20140111451 | Park | Apr 2014 | A1 |
20140114843 | Klein | Apr 2014 | A1 |
20140118520 | Slaby | May 2014 | A1 |
20140123275 | Azar | May 2014 | A1 |
20140143304 | Hegarty | May 2014 | A1 |
20140168093 | Lawrence | Jun 2014 | A1 |
20140196119 | Hill | Jul 2014 | A1 |
20140200953 | Mun | Jul 2014 | A1 |
20140223531 | Outwater | Aug 2014 | A1 |
20140244499 | Gruner | Aug 2014 | A1 |
20140250538 | Rapaport | Sep 2014 | A1 |
20140259130 | Li | Sep 2014 | A1 |
20140270571 | Dwan | Sep 2014 | A1 |
20140283059 | Sambamurthy | Sep 2014 | A1 |
20140283068 | Call | Sep 2014 | A1 |
20140289833 | Briceno | Sep 2014 | A1 |
20140317028 | Turgeman | Oct 2014 | A1 |
20140317726 | Turgeman | Oct 2014 | A1 |
20140317734 | Valencia | Oct 2014 | A1 |
20140317744 | Turgeman | Oct 2014 | A1 |
20140325223 | Turgeman | Oct 2014 | A1 |
20140325645 | Turgeman | Oct 2014 | A1 |
20140325646 | Turgeman | Oct 2014 | A1 |
20140325682 | Turgeman | Oct 2014 | A1 |
20140337786 | Luo | Nov 2014 | A1 |
20140344927 | Turgeman | Nov 2014 | A1 |
20150002479 | Kawamura | Jan 2015 | A1 |
20150012920 | De Santis | Jan 2015 | A1 |
20150062078 | Christman | Mar 2015 | A1 |
20150081549 | Kimberg | Mar 2015 | A1 |
20150091858 | Rosenberg | Apr 2015 | A1 |
20150094030 | Turgeman | Apr 2015 | A1 |
20150101031 | Harjanto | Apr 2015 | A1 |
20150128252 | Konami | May 2015 | A1 |
20150146945 | Han | May 2015 | A1 |
20150205944 | Turgeman | Jul 2015 | A1 |
20150205955 | Turgeman | Jul 2015 | A1 |
20150205957 | Turgeman | Jul 2015 | A1 |
20150205958 | Turgeman | Jul 2015 | A1 |
20150212843 | Turgeman | Jul 2015 | A1 |
20150213244 | Lymberopoulos | Jul 2015 | A1 |
20150213245 | Tartz | Jul 2015 | A1 |
20150213246 | Turgeman | Jul 2015 | A1 |
20150213251 | Turgeman | Jul 2015 | A1 |
20150242601 | Griffiths | Aug 2015 | A1 |
20150256528 | Turgeman | Sep 2015 | A1 |
20150256556 | Kaminsky | Sep 2015 | A1 |
20150264572 | Turgeman | Sep 2015 | A1 |
20150268768 | Woodhull | Sep 2015 | A1 |
20150279155 | Chun | Oct 2015 | A1 |
20150310196 | Turgeman | Oct 2015 | A1 |
20150348038 | Femrite | Dec 2015 | A1 |
20150358317 | Deutschmann | Dec 2015 | A1 |
20160006800 | Summers | Jan 2016 | A1 |
20160012465 | Sharp | Jan 2016 | A1 |
20160019546 | Eisen | Jan 2016 | A1 |
20160034673 | Chandra | Feb 2016 | A1 |
20160042164 | Goldsmith | Feb 2016 | A1 |
20160048937 | Mathura | Feb 2016 | A1 |
20160055324 | Agarwal | Feb 2016 | A1 |
20160057623 | Dutt | Feb 2016 | A1 |
20160077620 | Choi | Mar 2016 | A1 |
20160087952 | Tartz | Mar 2016 | A1 |
20160109969 | Keating | Apr 2016 | A1 |
20160132105 | Turgeman | May 2016 | A1 |
20160155126 | D'Uva | Jun 2016 | A1 |
20160164905 | Pinney Wood | Jun 2016 | A1 |
20160164906 | Pinney Wood | Jun 2016 | A1 |
20160174044 | Jones | Jun 2016 | A1 |
20160179245 | Johansson | Jun 2016 | A1 |
20160182503 | Cheng | Jun 2016 | A1 |
20160191237 | Roth | Jun 2016 | A1 |
20160196414 | Stuntebeck | Jul 2016 | A1 |
20160197918 | Turgeman | Jul 2016 | A1 |
20160209948 | Tulber | Jul 2016 | A1 |
20160226865 | Chen | Aug 2016 | A1 |
20160241555 | Vo | Aug 2016 | A1 |
20160294837 | Turgeman | Oct 2016 | A1 |
20160300049 | Guedalia | Oct 2016 | A1 |
20160300054 | Turgeman | Oct 2016 | A1 |
20160306974 | Turgeman | Oct 2016 | A1 |
20160307191 | Turgeman | Oct 2016 | A1 |
20160307201 | Turgeman | Oct 2016 | A1 |
20160321445 | Turgeman | Nov 2016 | A1 |
20160321689 | Turgeman | Nov 2016 | A1 |
20160328572 | Valacich | Nov 2016 | A1 |
20160342826 | Apostolos | Nov 2016 | A1 |
20160344783 | Kushimoto | Nov 2016 | A1 |
20160364138 | Luo | Dec 2016 | A1 |
20160366177 | Turgeman | Dec 2016 | A1 |
20160371476 | Turgeman | Dec 2016 | A1 |
20170011217 | Turgeman | Jan 2017 | A1 |
20170012988 | Turgeman | Jan 2017 | A1 |
20170017781 | Turgeman | Jan 2017 | A1 |
20170032114 | Turgeman | Feb 2017 | A1 |
20170034210 | Talmor | Feb 2017 | A1 |
20170048272 | Yamamura | Feb 2017 | A1 |
20170054702 | Turgeman | Feb 2017 | A1 |
20170063858 | Bandi | Mar 2017 | A1 |
20170076089 | Turgeman | Mar 2017 | A1 |
20170085587 | Turgeman | Mar 2017 | A1 |
20170090418 | Tsang | Mar 2017 | A1 |
20170091450 | Turgeman | Mar 2017 | A1 |
20170126735 | Turgeman | May 2017 | A1 |
20170127197 | Mulder | May 2017 | A1 |
20170140279 | Turgeman | May 2017 | A1 |
20170149958 | Xian | May 2017 | A1 |
20170154366 | Turgeman | Jun 2017 | A1 |
20170177999 | Novik | Jun 2017 | A1 |
20170193526 | Turgeman | Jul 2017 | A1 |
20170195354 | Kesin | Jul 2017 | A1 |
20170195356 | Turgeman | Jul 2017 | A1 |
20170221064 | Turgeman | Aug 2017 | A1 |
20170302340 | Berlin | Oct 2017 | A1 |
20170364674 | Grubbs | Dec 2017 | A1 |
20170364919 | Ranganath | Dec 2017 | A1 |
20180012003 | Asulin | Jan 2018 | A1 |
20180012227 | Tunnell | Jan 2018 | A1 |
20180034850 | Turgeman | Feb 2018 | A1 |
20180046792 | Toqan | Feb 2018 | A1 |
20180095596 | Turgeman | Apr 2018 | A1 |
20180097841 | Stolarz | Apr 2018 | A1 |
20180103047 | Turgeman | Apr 2018 | A1 |
20180107836 | Boger | Apr 2018 | A1 |
20180115899 | Kedem | Apr 2018 | A1 |
20180121640 | Turgeman | May 2018 | A1 |
20180160309 | Turgeman | Jun 2018 | A1 |
20180314816 | Turgeman | Nov 2018 | A1 |
20180349583 | Turgeman | Dec 2018 | A1 |
20180350144 | Rathod | Dec 2018 | A1 |
20180351959 | Turgeman | Dec 2018 | A1 |
20180373780 | Pascarella | Dec 2018 | A1 |
20190028497 | Karabchevsky | Jan 2019 | A1 |
20190057200 | Sabag | Feb 2019 | A1 |
20190121956 | Turgeman | Apr 2019 | A1 |
20190124068 | Anders | Apr 2019 | A1 |
20190156034 | Kedem | May 2019 | A1 |
20190158535 | Kedem | May 2019 | A1 |
20190220863 | Novick | Jul 2019 | A1 |
20190236391 | Novik | Aug 2019 | A1 |
20190272025 | Turgeman | Sep 2019 | A1 |
20190342328 | Rivner | Nov 2019 | A1 |
20190342329 | Turgeman | Nov 2019 | A1 |
20200012770 | Turgeman | Jan 2020 | A1 |
20200045044 | Turgeman | Feb 2020 | A1 |
20200076816 | Turgeman | Mar 2020 | A1 |
20200234306 | Turgeman | Jul 2020 | A1 |
Number | Date | Country |
---|---|---|
2410450 | Jan 2012 | EP |
2477136 | Jul 2012 | EP |
2541452 | Jan 2013 | EP |
2610776 | Jul 2013 | EP |
2646904 | Aug 2018 | EP |
3019991 | Feb 2019 | EP |
2338092 | May 2010 | ES |
2005099166 | Oct 2005 | WO |
2007146437 | Dec 2007 | WO |
2012001697 | Jan 2012 | WO |
2012073233 | Jun 2012 | WO |
2013161077 | Oct 2013 | WO |
2015127253 | Aug 2015 | WO |
2018007821 | Jan 2018 | WO |
2018007823 | Jan 2018 | WO |
2018055406 | Mar 2018 | WO |
Entry |
---|
Communication from the European Patent Office (EPO) in EP 14814408, dated Oct. 15, 2019. |
Bassam Sayed, “A Static Authentication Framework Based on Mouse Gesture Dynamics”, Helwan University, 2003. |
Communication from the European Patent Office (EPO) in EP 17739666, dated Jun. 17, 2020. |
International Search Report for PCT international application PCT/IL2018/051246, dated Mar. 11, 2019. |
Written Opinion of the International Searching Authority for PCT international application PCT/IL2018/051246, dated Mar. 11, 2019. |
Written Opinion of the International Searching Authority for PCT international application PCT/IL2011/000907, dated Apr. 19, 2012. |
Written Opinion of the International Searching Authority for PCT international application PCT/IB2014/062293, dated Oct. 1, 2014. |
Written Opinion of the International Searching Authority for PCT international application PCT/IB2014/062941, dated Dec. 17, 2014. |
Written Opinion of the International Searching Authority for PCT international application PCT/IB2016/054064, dated Jul. 9, 2015. |
Syed Ahsan Abbas et al., “What is the difference between a rooted and unrooted Android?” Quora.com, dated Jul. 22, 2016, printed on Aug. 12, 2019 from: www.Quora.com/What-is-the-difference-between-a-rooted-and-unrooted-Android. |
Sebastian Lindstrom, “Getting to know asynchronous JavaScript: Callbacks, Promises and Async / Await”, Medium.com, dated Jul. 2, 2017, printed on Aug. 12, 2019 from: Medium.com/codebuddies/getting-to-know-asynchronous-javascript-callbacks-promises-and-async-await-17e0673281ee. |
Machine translation of WO 2013/161077 A1, “Biometric authentication device, biometric authentication program, and biometric authentication method”, Obtained on Jan. 24, 2020 from: https://patents.google.com/patent/WO2013161077A1/en?oq=JP2006277341A. |
Oriana Riva et al., “Progressive authentication: Deciding when to authenticate on mobile phones”, USENIX Security Symposium 2012. |
Ahmed et al., “A New Biometric Technology Based on Mouse Dynamics”, Jul.-Sep. 2007, IEEE Transactions on Dependable and Secure Computing, vol. 4, No. 3, pp. 165-179. |
Bailey, Kyle O., “Computer Based Behavioral Biometric Authentication Via Multi-Modal Fusion”, Thesis, 2013, Air Force Insitute of Technology. |
Elizabeth Stinson and John C. Mitchell, “Characterizing the Remote Control Behavior of Bots”, Detection of Intrusions and Malware, and Vulnerability Assessment. Springer Berlin Heidelberg, p. 89-108. Dec. 31, 2007. |
Todorov, “Optimality Principles in Sensorimotor Control (Review)”, Sep. 2004, Nature Neuroscience 7, pp. 907-915. |
Cleeff et al., “Security Implications of Virtualization: A Literature Study”, Science and Engineering, 2009. |
Hibbeln et al., “Detecting Deception in Online Environments: Measuring Fraud Through Mouse Cursor Movements”, Jun. 7, 2014, Gmunden Retreat on NeuroIS 2014 Gmunden Austria, p. 38. |
Ferrie Peter, “Attack on Virtual Machine Emulators”, Symantec Technology Exchange, 2007. |
Yampolskiy et al., “Behavioural Biometrics: a survey and classification”, 2008, International Journal of Biometrics, vol. 1, No. 1, pp. 81-113. |
Provos et al., 2007, “The Ghost in the Browser: Analysis of Web-based Malware”. |
Huang Yao-Wen et al., “Web application security assessment by fault injection and behavior monitoring”, 2003, Proceedings of the 12th international conference on World Wide Web, ACM. |
Ben Hansen, “The Blur Busters Mouse Guide”, dated Feb. 1, 2014; printed from the Internet on Aug. 5, 2019 from: https://www.blurbusters.com/faq/mouse-guide/. |
Chris Cain, “Analyzing Man-in-the-Browser (MITB) Attacks”, dated Dec. 2014; downloaded from the Internet on Aug. 5, 2019 from: https://www.sans.org/reading-room/whitepapers/forensics/analyzing-man-in-the-browser-mitb-attacks-35687. |
Faisal Alkhateeb et al., “Bank Web Sites Phishing Detection and Notification System Based on Semantic Web technologies”, International Journal of Security and its Applications 6(4):53-66, Oct. 2012. |
Sungzoon Cho et al., “Artificial Rhythms and Cues for Keystroke Dynamics Based Authentication”, International Conference on Biometrics (ICB)—Advances in Biometrics, pp. 626-632, year 2006. |
International Search Report for PCT/IB2017/055995, dated Feb. 15, 2018. |
Written Opinion of the International Search Authority for PCT/IB2017/055995, dated Feb. 15, 2018. |
Supplementary European Search Report for Application 11844440 dated Nov. 17, 2017. |
International Search Report for application PCT/IB2016/054064 dated Nov. 21, 2016. |
International Search Report for application PCT/IB2014/062941 dated Dec. 17, 2014. |
International Search Report for application PCT/IB2014/062293 dated Oct. 1, 2014. |
International Search Report for application PCT/IL2011/000907 dated Apr. 19, 2012. |
Nakkabi et al., “Improving Mouse Dynamics Biometric Performance Using Variance Reduction via Extractors with Separate Features”, Nov. 2010, IEEE Transactions on System, Man, and Cybernetics; vol. 40, No. 6. |
Nance et al., “Virtual Machine Introspection”, IEEE Security & Privacy, 2008. |
Garfinkel and Rosenblum, “A virtual Machine Introspection-Based Architecture for Intrusion Detection.”, 2003, Proc. Network and Distributed Systems Security Symp., The Internet Society, pp. 191-206. |
Spafford et al., “Software Forensics: Can We Track Code to its Authors?”, Feb. 1992, Computer Science Technical Report, Purdue e-Pubs, Report No. CSD-TR-92-010. |
Tavis Ormandy, “An Empirical Study into the Security Exposure to Hosts of Hostile Virtualized Environments”, retrieved from the Internet on May 3, 2017, from: http://taviso.decsystem.org/virtsec.pdf. |
Zheng et al., “An Efficient User Verification System via Mouse Movements”, Oct. 17-21, 2011, CCS'11, Chicago, Illinois. |
Liston et al., “On the Cutting Edge: Thwarting Virtual Machine Detection”; retrieved from the Internet on May 3, 2017, from: http://docplayer.net/9791309-On-the-cutting-edge-thwarting-virtual-machine-detection.html. |
Georgia Frantzeskou et al., “Identifying Authorship by Byte-Level N-Grams: The source Code Author Profile (SCAP) Method”, Spring 2007, International Journal of Digital Evidence, vol. 6, issue 1. |
Franklin et al., “Remote Detection of Virtual Machine Monitors with Fuzzy benchmarking”, ACM SIGOPS Operating Systems Review, V42, Issue 3, Apr. 2008. |
Emmanouil Vasilomanolakis, “A honeypot-driven cyber incident monitor: Lessons learned and steps ahead”; Sep. 2015; SIN '15: Proceedings of the 8th International Conference on Security of Information and Networks; Publisher: ACM; pp. 1-7. |
Number | Date | Country | |
---|---|---|---|
20200327422 A1 | Oct 2020 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 15192845 | Jun 2016 | US |
Child | 16902289 | US |