IDENTIFYING AND AUTHENTICATING USERS BASED ON PASSIVE FACTORS DETERMINED FROM SENSOR DATA

Abstract

The disclosed embodiments relate to a system that authenticates and/or identifies a user of an electronic device based on passive factors, which do not require conscious user actions. During operation of the system, in response to detecting a trigger event, the system collects sensor data from one or more sensors in the electronic device. Next, the system extracts a feature vector from the sensor data. The system then analyzes the feature vector to authenticate and/or identify the user, wherein the feature vector is analyzed using a model trained with sensor data previously obtained from the electronic device while the user was operating the electronic device.

Description

BACKGROUND

Field

The disclosed embodiments generally relate to techniques for identifying and authenticating users in computing systems. More specifically, the disclosed embodiments relate to a technique for identifying and authenticating a user in a computing system based on passive factors determined from sensor data.

Related Art

There presently exist a number of systems for identifying and authenticating computer system users. At present, most systems rely on knowledge-based factors, such as passwords. However, passwords have limitations, especially with respect to the user experience. Human users are simply not good at creating new passwords that include strong and unique combinations of characters that are also memorable. Furthermore, passwords are commonly phished or stolen. Moreover, the password-creation rules that websites and services enforce are ever-changing and growing increasingly complex. To keep up with this complexity, users often reuse passwords across multiple services, or make only small, predictable changes among passwords for different services. Also, because passwords are hard to remember, users often write them down or store them in a file for easy access, which also makes them easier to steal. Some users employ password managers to handle all of their passwords. However, password managers reduce security by creating a single point of failure.

Services commonly make use of other knowledge-based queries for authentication, such as asking for a user's mother's maiden name, Social Security number, or information from the user's credit report. However, this type of data is often easy to research or is susceptible to social-engineering attacks.

Some services rely on a two-factor authentication technique, which requires a user to carry an extra device in order to authenticate. However, this can be burdensome to the user because the device can be forgotten, run out of power, or break.

Some services authenticate a user based on biometric factors, such as fingerprints. However, it is often inconvenient to use such systems, and they can require specialized hardware. Moreover, it is very difficult or impossible to alter a biometric signature in case it is compromised.

Another technique is to authenticate users based on certain types of passive factors, such as cookies, IP addresses, and physical locations. In systems that employ such passive factors, users do not have to do anything additional to identify themselves. However, such passive factors can only separate users into large classes, and are generally not accurate enough to authenticate a particular user. Such techniques are too imprecise in part because they tend to focus on identifying a device, instead of identifying a specific user of the device.

Some systems allow users to employ third-party services to provide authentication. However, these third-party services have a number of drawbacks, including giving up control of authentication to a potentially competing interest, and the absence of a predominant standard for authentication and/or identity.

Hence, what is needed is a technique for identifying and authenticating users of computing systems without drawbacks of the above-described existing techniques.

SUMMARY

The disclosed embodiments relate to a system that authenticates and/or identifies a user of an electronic device based on passive factors, which do not require conscious user actions. During operation of the system, in response to detecting a trigger event, the system collects sensor data from one or more sensors in the electronic device. Next, the system extracts a feature vector from the sensor data. The system then analyzes the feature vector to authenticate and/or identify the user, wherein the feature vector is analyzed using a model trained with sensor data previously obtained from the electronic device while the user was operating the electronic device.

In some embodiments, the electronic device is a portable electronic device, and the sensor data includes movement-related sensor data caused by movement of the portable electronic device while the portable electronic device is in control of the user.

In some embodiments, the movement-related sensor data includes accelerometer data gathered while the user is walking, wherein the accelerometer data reflects a characteristic gait of the user while walking.

In some embodiments, authenticating and/or identifying the user of the electronic device involves generating a security score for the user along with an associated confidence value.

In some embodiments, if the security score does not exceed a minimum value, the system causes a challenge to be issued to the user. If the user successfully responds to the challenge, the system authenticates and/or identifies the user.

In some embodiments, extracting the features for the collected data involves using signal-processing techniques to extract the features.

In some embodiments, the model was trained using a machine-learning technique.

In some embodiments, if the user is successfully authenticated and/or identified, the system automatically communicates a username and password to a website or application, which the user is attempting to access.

In some embodiments, the trigger event comprises one of the following: a detected activity of the user; a state change associated with the electronic device; a timer-based trigger; and a broadcast trigger received by the electronic device.

In some embodiments, the one or more sensors include one or more of the following: an accelerometer; a touchscreen; a gyroscope; an inertial sensor; an ambient light sensor; an image sensor; a camera; an odor sensor; a temperature sensor; a barometric-pressure sensor; a cellular radio signal strength sensor; a Bluetooth radio signal strength sensor; a near-field communication (NFC) sensor; a network-proximity sensor; an infrared sensor; a magnetometer; a battery sensor; a force-touch measurement sensor; a multi-touch measurement sensor; a sensor in a mouse; a sensor in a trackpad; and a keyboard-timing sensor.

The disclosed embodiments relate to a system that automatically enters login credentials into a website on behalf of a user. During operation, the system detects a login form while accessing a web page on the website. In response to detecting the login form, the system attempts to authenticate the user through an alternative authentication technique. If the user is successfully authenticated, the system automatically responds to the login form by submitting previously stored login credentials for the user.

In some embodiments, if a challenge is received from the website in response to submission of the login credentials, the system automatically responds to the challenge using previously stored user information.

In some embodiments, if the user is not successfully authenticated using the alternative authentication technique, the system indicates an error and reverts to an original authentication technique.

In some embodiments, the login credentials comprise a username and a password.

In some embodiments, the system also interacts with a change-password mechanism on the website to automatically change the password for the user.

In some embodiments, the password is automatically changed each time the user accesses the website.

BRIEF DESCRIPTION OF THE FIGURES

FIG. 1 illustrates various computing devices and sensors in the vicinity of a user in accordance with the disclosed embodiments.

FIG. 2 illustrates an authentication process in accordance with the disclosed embodiments.

FIG. 3 illustrates how authentication agents interact with the authentication system in accordance with the disclosed embodiments.

FIG. 4 illustrates how data is processed by the authentication system in accordance with the disclosed embodiments.

FIG. 5 presents a flow chart illustrating operations involved in the authentication process in accordance with the disclosed embodiments.

FIG. 6 presents a flow chart illustrating operations a client performs during the authentication process in accordance with the disclosed embodiments.

FIG. 7 presents a flow chart illustrating operations performed during an automated login process in accordance with the disclosed embodiments.

FIG. 8 presents a flow chart illustrating a process for automatically changing a password for a user in accordance with the disclosed embodiments.

DETAILED DESCRIPTION

The following description is presented to enable any person skilled in the art to make and use the present embodiments, and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present embodiments. Thus, the present embodiments are not limited to the embodiments shown, but are to be accorded the widest scope consistent with the principles and features disclosed herein.

The data structures and code described in this detailed description are typically stored on a computer-readable storage medium, which may be any device or medium that can store code and/or data for use by a computer system. The computer-readable storage medium includes, but is not limited to, volatile memory, non-volatile memory, magnetic and optical storage devices such as disk drives, magnetic tape, CDs (compact discs), DVDs (digital versatile discs or digital video discs), or other media capable of storing computer-readable media now known or later developed.

The methods and processes described in the detailed description section can be embodied as code and/or data, which can be stored in a computer-readable storage medium as described above. When a computer system reads and executes the code and/or data stored on the computer-readable storage medium, the computer system performs the methods and processes embodied as data structures and code and stored within the computer-readable storage medium. Furthermore, the methods and processes described below can be included in hardware modules. For example, the hardware modules can include, but are not limited to, application-specific integrated circuit (ASIC) chips, field-programmable gate arrays (FPGAs), and other programmable-logic devices now known or later developed. When the hardware modules are activated, the hardware modules perform the methods and processes included within the hardware modules.

Computing Environment

FIG. 1 illustrates various computing devices and associated sensors that comprise a computing environment 100 for a user 102 in accordance with the disclosed embodiments. As illustrated in FIG. 1, the computing environment 100 surrounding user 102 includes a number of portable computing devices, such as a smartphone 104, or a wearable device 108, such as a fitness tracker or a smartwatch. The user 102 may also be operating a laptop computer 106 or possibly a desktop computer (not shown).

These computing devices typically include sensors that can be used to uniquely identify the user, or verify that an action is legitimately performed by the user. For example, mobile devices, such as smartphone 104, wearable device 108, a tablet computer or other personal electronic device, include sensors such as: a touchscreen; an accelerometer; a gyroscope; an inertial sensor; a virtual keyboard-timing sensor; an ambient light sensor; a camera; an odor sensor; a temperature sensor; a barometric-pressure sensor; a cellular radio signal strength sensor; a Bluetooth radio signal strength sensor; a near-field communication (NFC) sensor; an infrared sensor; a battery sensor; a force-touch measurement sensor; and a multi-touch measurement sensor. Similarly, laptop computer 106 or a desktop computer may include sensors, such as: a keyboard-timing sensor; a mouse sensor; a trackpad sensor; a Bluetooth radio signal strength sensor; an image sensor or camera; a network proximity sensor; an infrared sensor; and a battery sensor.

Computing environment 100 can include other devices with sensors, which are located in, on or near a person's body, including: medical indigestibles, subdermal implants, electronic tattoos, smart clothing or accessories, and physical authentication devices.

In addition, computing environment 100 can include other devices in the vicinity of user 102 having sensors and network connectivity, such as: a camera 103, a Wi-Fi® access point 110, a Bluetooth™ beacon 112, a home thermostat, automobile components, security systems, televisions and other entertainment devices, and IoT (Internet of Things) devices.

Note that the sensors can also provide side-channel information gleaned from measurements not necessarily designed to directly measure the element in question, such as: an accelerometer; a gyroscope; an ambient light sensor; a magnetometer; a barometer; a proximity sensor; a thermometer; and an image sensor.

Moreover, the data obtained from the sensors can be related to the interaction of multiple devices, such as: (1) the presence of different devices within wireless range or on the same local network; (2) the relative signal strength, noise, packet loss, bandwidth readings, or other statistics among multiple devices, or between a mobile device such as a mobile phone and a fixed device such as a wireless access point; (3) a combination of audio data from multiple microphones that measure ambient noise; (4) audio signals generated by playing sounds on speakers and listening for those sounds or echoes of those sounds on nearby microphones; (5) signals obtained by recording ambient light data from multiple light sensors; and (6) signals that indicate when a device is attached/paired with another device, or comes into range or communication with the other device (or when a device is detached/unpaired or goes out of range).

Also, data obtained from sensors can include semantic information about the usage of a service, such as: (1) a specific sequence of interactions with the service and the timings between the interactions; (2) when there exist multiple ways to perform a task, the particular user flow used to perform the task; (3) mistakes, typos, or misclicks, or other operations that are typically ignored by the service; (4) metadata about specific interactions, such as what part of a button or screen element was clicked, or readings from other sensors before, during, or after a significant event; and (5) responses and changes in user behavior due to perceptible or imperceptible changes in how a service is rendered or results are presented.

Exemplary Authentication Process

Prior to the authentication process taking place, the user performs a number of initialization operations, such as installing software agents on the user's devices, and importing password data from a password-management system. Next, the system learns familiar user behaviors based on information obtained from the user's devices over time to produce one or more models of the user's behaviors. After these initialization operations are complete, the system is ready to perform the authentication process.

Next, as illustrated by the example in FIG. 2, the system performs the authentication process. As shown in FIG. 2, during operation of a smartphone 204, a trigger event 202 occurs, which causes an agent running on smartphone 204 to collect sensor data 206. Next, the smartphone 206 performs a feature-extraction operation 208 on the sensor data 206 to produce a feature vector 210, which is communicated to a cloud server 212. Cloud server 212 then uses a model generated through a machine-learning process to determine a security score and associated confidence value 214 for a user, wherein the security score indicates a probability that the sensor data 206 is associated with the user.

Authentication System

FIG. 3 illustrates how authentication agents 302 and 304 operate in an exemplary authentication system 300 in accordance with the disclosed embodiments. Within authentication system 300, authentication agents 302 and 304 are responsible for handling integration with authentication mechanisms on various sites and services. In some embodiments, authentication agents 302 and 304 are implemented as browser plugins that control user-authentication operations that take place in associated web browsers.

For example, an authentication agent 304 in a login system can perform operations, such as modifying a document object model (DOM), structure, or look/styling of a web page, service, application, or user interface to add new login mechanisms, or to modify existing login mechanisms to facilitate automated authentication and login processes as is described in more detail below. These operations can involve: automatically interacting with user-interface elements; automatically filling in credentials; and interfacing directly with existing authentication mechanisms and interfaces. While performing these operations, authentication agent 304 can optionally hide authentication-related elements, such as usernames, passwords, forgotten-password links, and other elements so as to allow the user authentication operation to proceed without involving explicit user action.

Authentication agents 302 and 304 can also analyze the security of a user's profile and suggest actions for increasing security. For example, while analyzing a user's security profile, an authentication agent can consider: (1) the strength of the user's password with respect to dictionaries, known password leaks, password reuse, and complexity measurements; (2) an amount of information that is known about a user's behavior or environment; (3) how unique a user's behavior and environment are in comparison to those of other users; (4) the security of the user's friends or contacts; (5) the number and variety of devices that a user has registered; and (6) how many active factors have been registered for the user.

Authentication agents 302 and 304 can also enable the user to provide additional information about themselves or their devices. For example, the user can disclose familiar devices by performing: a network probe; a Bluetooth scan; an account sync; and a device-to-device sync. The user can also answer questions about themselves, and can explicitly register devices, biometrics, or any other information that will be used to respond to active or passive challenges.

The authentication agent can also use hints to discover when a device is being used by a different user, such as looking at when the user logs in to a different account, and looking for anomalous access patterns. Note that the system can possibly allow a user to authorize the use of their device(s) by one or more alternative users, which involves: ceasing collection of data for the main user; and synchronizing the alternative user's sampled data across all of the main user's accounts.

While performing authentication operations, authentication agents 302 and 304 communicate with local authentication database instances 306 and 308, respectively, which store credentials, usernames, passwords, secrets, cookies, tokens, and other secure items required for authentication. In the embodiment of the system illustrated in FIG. 3, there exists one instance of a local authentication database for each instance of an authentication agent. Moreover, the data in local authentication databases 306 and 308 can be synchronized by a synchronization module 316, so that local copies of the data are consistent with a master copy of the data stored in a global authentication database 318. For example, this synchronization process enables an encrypted password state to be synchronized across multiple devices.

Processing Sensor Data

FIG. 4 illustrates how sensor data is processed by the authentication system in accordance with the disclosed embodiments. As illustrated in FIG. 4, the authentication system provides a query component 314 for its clients, such as authentication agent 304 and other clients 442, to query for purposes of verifying identity. Authentication agent 304 and other clients 442 can access query component 314 to verify a user's identity for a number of reasons, including logging on, checking out, and performing other secure actions.

During operation of the system illustrated in FIG. 4, sensors 401-403 collect raw sensor data 411-413 associated with a user's behavior, actions, and/or environment. Then, processors 421-422 perform signal-processing operations and other techniques on raw sensor data 411-413 to extract feature vectors. Note that processors 421-422 can be incorporated into a sensor, or can reside on a local device near the sensor, or on an entirely separate device.

Moreover, the signal-processing operations performed by processors 421-422 can include: filtering operations; conversions among the time, space and frequency domains; Fourier transforms; Butterworth filters, Z-plane analysis operations, wavelet transforms, or other operations to extract information from signals. Also, note that feature vectors 423-424 can include timestamps associated with specific sensor data collected on a per-sensor basis. Processors 421-422 can also extract encryption key bits from biometric/behavioral factors, and can combine them with other bits to form encryption keys that can be used to decrypt sensitive data. Next, processors 421-422 buffer feature vectors 423-424 and send them to database service 431, which aggregates and stores feature vectors obtained from multiple processors.

Analysis component 441 then queries database service 431 to obtain feature vectors 423-424, and performs various analysis and machine-learning operations to correlate the data and generate one or more security scores and associated identifiers 442.

Analysis component 441 uses prior data about a user obtained from database service 431 to build one or more models for the user. During this model-building process, the system can focus on characteristics of specific user behaviors to uniquely identify a user. For example, the system can examine accelerometers readings (or other sensor readings), which indicate how a user: walks, stands up, sits down, talks or types. The system can also focus on how a user manipulates her phone. One promising way to authenticate a user is to recognize the user based on accelerometer readings indicating characteristics of the user's gait while the user is walking. In fact, it is possible to recognize a specific user based on just the magnitude of the accelerometer data, and not the direction of the accelerations. The system can also consider combinations of factors from different sensors instead of merely considering a single factor. This includes considering cross-device factors, such as signal strength between a wearable device and a user's smartphone, or a combination of accelerometer readings from the wearable device and the smartphone.

The system can also attempt to detect the presence of another person, for example by looking for a Bluetooth signal from the other person's smartphone, and can condition the recognition process based on the presence or absence of the other person. This can be useful because the presence of another person may change the user's behavior.

Next, while processing the feature vectors, analysis component 441 can generate one or more possible user identities with an associated security score for each identity. Note that the system illustrated in FIG. 4 can also include a “challenge channel” (not shown) to deliver challenges to a device or a user as is discussed in more detail below.

Authentication agent 304 and other clients 442 can then connect to the query component 314 to retrieve the security score 310 for a user from analysis component 441. Query component 314 can also be used by clients to query and verify user identities continuously throughout the usage of their service. Also, instead of merely identifying and authenticating a specific user, the system can potentially be used to determine whether a user's smartphone has been stolen, or borrowed, or if another user is trying to log into a user's device on behalf of the user.

Authentication Process

FIG. 5 presents a flow chart illustrating operations involved in the authentication process in accordance with the disclosed embodiments. First, the system detects a trigger event (step 502). As mentioned above, this trigger event can involve: detecting an activity of the user (such as detecting whether the user is walking, stationary, or driving a car); a state change associated in an electronic device belonging to a user (such as a smartphone waking up, changing its charging state, going in and out of range of a wireless access point, or moving a certain distance); a timer-based trigger; and a broadcast trigger received by the electronic device.

In response to detecting the trigger event, the system starts data collection (step 504) and sometime later stops data collection (step 506). Then, the system performs signal-processing operations on the data to produce a feature vector (step 508). The system then uses a model generated using machine-learning techniques (such as a neural network) to process the feature vector (step 510). Note that the system may generate a number of models for each user, wherein each model is associated with a specific behavior, such as walking, standing up or sitting down. The system can also generate a “universal background model,” which ideally includes characteristics for the entire human race, and can determine how the user fits into the universal background model. In particular, the system can use the universal background model to identify “similar people” who exhibit characteristics, which are closest to the user, and can construct synthetic training data to train the model to discriminate between the user and the similar people.

Finally, the system generates a security score for the user along with an associated confidence value (step 512). Note that while determining the security score, the system can generate a “generalized product of experts.” For example, the system can include a collection of experts, such as an expert that determines whether sensor data matches a user's gait, and another expert that determines a user's location. The system can then use inputs from all of these experts to generate the security score.

FIG. 6 presents a flow chart illustrating operations a client performs during the authentication process in accordance with the disclosed embodiments. First, the client sends a query to the query component asking to authenticate a user (step 602). The client then receives a security score from the query component in response to the query (step 604). Then, the system determines whether the security score is greater than a threshold (step 606). (Note that the threshold can be different for different services and actions.) If the security score is greater than the threshold (YES at step 606), the client authenticates the user (step 612). In some embodiments, this may involve combining a cryptographically signed response received from the query component with local cryptographic data to perform the authentication operation.

Otherwise, if the security score is not greater than the threshold (NO at step 606), the client causes a challenge to be issued to the user (step 608) either on the same device or on a different device. The challenge can be an “active challenge” that requires the user to perform some action, or a “passive challenge” that happens unbeknownst to the user and requires the system to obtain more-detailed sensor data or perform more-sophisticated processing of the sensor data.

A challenge can involve asking the user about a knowledge-based factor, such as asking the user to: provide a password or PIN; answer a security question; identify friends in photos; answer a question about where the user was at a particular time/date, or who was with the user, optionally with photos. A knowledge-based factor can also involve asking a user: if they took a particular photo; about credit card charges or payment activity; about emails, text messages, or other communications; about information from their social media profiles or their résumé; to identify an item in a picture; or about the user's habits, behavior, or history. Responding to a challenge can also involve using biometrics to provide authentication, which may involve obtaining: a fingerprint or other biometric reading; facial recognition; an image of the user or user's surroundings taken by a device's camera; and a voiceprint.

Responding to a challenge can also involve using additional factors to authenticate, including: a text message/email/voice call; a challenge/response to a phone app; a photo ID (holding the user's license in front of a camera); a USB unlock key; a YubiKey; a U2F key; another device with a unique ID; a one-time-use unlock code; or an NFC “bump” between a wearable device and a mobile device.

The user can also use unique behaviors to authenticate, including: signing the user's name; saying a phrase; drawing a pattern; performing a personalized motion in front of a motion-capture device; and singing or whistling.

Then, the system determines whether the user successfully responded to the challenge (step 610). If so (YES at step 610), the client authenticates the user (step 612). Otherwise, if the user does not successfully respond to the challenge (NO at step 610), the client does not authenticate the user (step 614). Also, if the security score of a user drops below or goes above the threshold, the query component can actively push notifications about the change to registered clients.

Automated Login Process

FIG. 7 presents a flow chart illustrating operations performed during an automated login process in accordance with the disclosed embodiments. First, the system downloads HTML for a web page from a website (step 702). Next, the system detects a login form in the HTML (step 704). The system then uses an alternative authentication mechanism instead of the login form (step 706). In particular, the alternative authentication mechanism can involve authenticating the user based on passive factors based on sensor data, which do not require conscious user actions. The system then determines whether the user was authenticated by the alternative login mechanism (step 708). If so (YES at step 708), the system sends previously stored login credentials (i.e., a username and a password) to the website in response to the login form (step 710). Otherwise, if the user was not successfully authenticated by the alternative login mechanism (NO at step 708), the system indicates an error and possibly reverts to the original authentication technique (step 712), which for example can involve presenting the login form to the user.

Note that the above-described automated login process provides a mechanism for an authentication system that uses passive factors to be used with a legacy website or service, which relies on passwords for authentication.

Automated Password Changing

There exist a number of reasons for changing passwords. Prior to logging in, a password may be unknown or may not work. Moreover, after logging on, it may be desirable to change a password for security reasons, because a frequently changing password is harder to compromise than a password that does not change. In fact, if the password is changed every time a user logs on, the password effectively becomes a “one-time-use” code, which is extremely secure. It may also be desirable to change a password in response to a security alert about a weakness of the current password.

The process of manually changing a password is cumbersome and can degrade the user experience. Hence, it is desirable to produce a system that automates the password-changing process. Such an automated system can operate by simulating user interactions with “forgot password” or “change password” functionality of a service, or by interacting with a “password change” or “password reset” application-programming interface (API). While performing the operations to change the password, it is also desirable to hide the operations from the user, which may involve performing the operations on a client or a server.

The automated password-change system must come up with a valid new password that obeys system-specific password rules. This can be accomplished by parsing the text of the rules, or through trial-and-error and associated parsing of resulting error messages. The new password can also be biometrically generated, for example by turning a user's walking gait into part of a cryptographic key.

During operation, the automated password-changing system must receive any challenges that arise and effectively respond to such challenges. These challenges may require a response through email, which can involve reusing existing cookies or sessions to access an email account for the user, or using the user's email credentials to access the user's email via IMAP or some other protocol. It is also desirable to be able to automatically archive or delete any email messages related to the challenge and confirmation processes. Such challenges may also involve SMS text messages, which may require an agent on a smartphone to capture and respond to text messages, and to automatically archive and/or delete challenge-related text messages. Such challenges may also involve a phone call from a service provider, which may require the system to: automatically answer the phone; wait for the call to go to voicemail; or send the call to voicemail, and subsequently access the voicemail recording. In such cases, it may be necessary to use speech-recognition technology to parse the challenge information, or to use a third-party service or an answering service to provide speech recognition.

In summary, FIG. 8 presents a flow chart illustrating a process for automatically changing a password for a user in accordance with the disclosed embodiments. During operation, the system interacts with a change-password mechanism on a website to automatically change the password for the user (step 802). In some embodiments, the password is automatically changed each time the user accesses the website.

Advantages

The above-described authentication techniques provide a number of advantages. For example, these authentication techniques can be used to: identify the user of a device; enable a user to securely manage identity while online; eliminate passwords and two-factor physical authentication from the user experience; utilize passive factors for seamless usability; provide a third-party authentication and user validation service; provide user-device security by notifying the user about unauthorized usage across all of the user's devices; reduce e-commerce fraud; differentiate between human users and nonhuman (bot) users; distinguish between legitimate and malicious users; allow secure messaging between individuals, regardless of the devices used; facilitate payments to a specific individual, rather than to a specific device or an account; facilitate the processing of contracts involving multiple individuals and certifications that the individuals performed certain actions; and automatically prevent fraudulent usage of a service.

The above-described authentication techniques also have advantages over existing authentication techniques because they rely on behavioral actions and other environmental data obtained from sensors in multiple sources and hence require no conscious user action. They can also eliminate the need for external authentication devices, and can facilitate automatic password resetting, rotation, and generation in the background.

Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present invention. Thus, the present invention is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The foregoing descriptions of embodiments have been presented for purposes of illustration and description only. They are not intended to be exhaustive or to limit the present description to the forms disclosed. Accordingly, many modifications and variations will be apparent to practitioners skilled in the art. Additionally, the above disclosure is not intended to limit the present description. The scope of the present description is defined by the appended claims.

Claims

1-22. (canceled)

23. A method for automatically entering login credentials into a website on behalf of a user, comprising: detecting a login form while accessing a web page on the website;in response to detecting the login form, attempting to authenticate the user via an alternative passive authentication process that does not require conscious action of the user; andif the user is successfully authenticated through the alternative passive authentication process, automatically responding to the login form by submitting previously stored login credentials for the user.

24. The method of claim 23, wherein, upon receipt of a challenge from the website in response to submission of the login credentials, the method further comprises automatically: responding to the challenge using previously stored user parameters.

25. The method of claim 23, wherein responsive to the user not being successfully authenticated using the alternative passive authentication process, the method further comprising: indicating an error and reverting to an original authentication process.

26. The method of claim 23, wherein the login credentials comprise a username and a password.

27. The method of claim 26, further comprising: interacting with a change-password mechanism on the website to automatically change the password for the user.

28. The method of claim 27, further comprising: changing the password responsive to one or more further accesses of the website.

29. A method comprising: determining, via a login program, a user attempt to supply authentication credentials;responsive to determining the user attempt, transitioning the login program to respond to alternative passive authentication credentials, which do not require conscious user actions;submitting the alternative passive authentication credentials; andpermitting the user to access content responsive to the submitted alternative passive authentication credentials.

30. The method of claim 29, wherein permitting the user to access content comprises permitting the user to access a voicemail message.

31. The method of claim 29, wherein permitting the user to access content comprises permitting the user to access an email account.

32. The method of claim 29, wherein permitting the user to access content comprises displaying content from a website.

33. An apparatus comprising: a processor coupled to at least one memory to: determine, via a login program, a user attempt to supply authentication credentials;responsive to determining the user attempt, transition the login form to respond to alternative passive authentication credentials, which do not require conscious user actions;submit the alternative passive authentication credentials; andpermit the user to access content responsive to the submitted alternative passive authentication credentials.

34. The apparatus of claim 33, wherein the processor coupled to the at least one memory are additionally to: indicate receipt of a challenge in response to submission of the authentication credentials; andrespond to the challenge using previously stored user parameters.

35. The apparatus of claim 33, wherein the processor coupled to the at least one memory are additionally to: indicate an error and revert to an original authentication process.

36. The apparatus of claim 33, wherein the processor coupled to the at least one memory are additionally to: interact with a change-password mechanism on a website to change the password for the user without user input.

37. The apparatus of claim 33, wherein the processor coupled to the at least one memory to permit the user to access content are to: permit the user to access a voicemail message.

38. The apparatus of claim 33, wherein the processor coupled to the at least one memory to permit the user to access content are to: permit the user to access an email account.

39. The apparatus of claim 33, wherein the processor coupled to the at least one memory to permit the user to access content are to: permit the user to access displayed content from a website.

40. An article comprising: a non-transitory storage medium having instructions stored thereon which, when executed by a processor coupled to at least one memory, cause the processor coupled to the at least one memory to: determine, via a login program, a user attempt to supply authentication credentials;responsive to determining the user attempt, transition the login form to respond to alternative passive authentication credentials, which do not require conscious user actions;submit the alternative passive authentication credentials; andpermit the user to access content responsive to the alternative passive authentication credentials.

41. The article of claim 40, wherein the non-transitory storage medium includes instructions that are additionally to: indicate receipt of a challenge in response to submission of the authentication credentials; andrespond to the challenge using previously stored user parameters.

42. The article of claim 40, wherein the non-transitory storage medium includes instructions that are additionally to: indicate an error and revert to an original authentication process.