Abstract: The embodiments disclosed herein relate to a biometric information registration apparatus and method using an artificial neural network. According to an embodiment, there are disclosed a biometric information registration apparatus and method that register biometric information by deriving converted information and a biometric information template based on an artificial neural network formed by successively connecting an encoding network for extracting security information and a feature point extraction network for extracting feature points to each other and renew the biometric information template using the converted information when updating the artificial neural network.

Abstract: A system and method for modification of a passcode for accessing the system are provided. The system includes a premises control unit. The premises control unit including control processing circuitry configured to: receive an expected code message, the expected code message instructing an initiation to monitor for an input from a user, receive a input code that is input by the user, determine whether the input code matches a predefined verification code, and if the input code matches the predefined verification code, cause transmission of a verification message to a monitoring server, the verification message indicating the input code matched the predefined verification code and triggering the monitoring server to allow a passcode for accessing the system to be modified.

Abstract: An invisible intercom and access system and method. The invisible intercom and access system may include a visitor device configured to make a phone call to a specific phone number; one or more authorized point of contact (APoC) device configured to receive the phone call and having an input configured to receive a code that produces tones; one or more third party device configured to control access to one or more access point of a property or building; and an invisible intercom and access apparatus configured to receive the phone call from the visitor device and connect the phone call to the one or more APoC device, recognize the tones of the code input at the one or more APoC device, and control or send a control signal to the one or more third party device.

Abstract: The present invention relates to a weight management method and system for neural network processing. The method includes two stages, i.e., off-chip encryption stage and on-chip decryption stage: encrypting trained neural network weight data in advance, inputting the encrypted weight into a neural network processor chip, and decrypting the weight in real time by a decryption unit inside the neural network processor chip to perform related neural network calculation. The method and system realizes the protection of weight data without affecting the normal operation of a neural network processor.

Abstract: A device includes memory and a processor. The device receives biometric information. The device receives location information. The device analyzes the received biometric information with stored biometric information. The device analyzes the received location information with stored location information. The device determines whether the received biometric information matches the stored biometric information. The device determines whether the received location information matches the stored location information. The device sends an electronic communication that indicates whether the received biometric information matches the stored biometric information and whether the received local information matches the stored location information.

Abstract: In an approach to adjusting user permissions based on mental acuity, one or more computer processors determine whether an individual is within a threshold proximity to a monitored location. In response to determining that an individual is within a threshold proximity to the monitored location, the one or more computer processors identify a required mental acuity for the monitored location. The one or more computer processors determine a current mental acuity for the individual. The one or more computer processors compare the determined mental acuity for the individual with the required mental acuity for the monitored location.

Abstract: A method of speaker recognition comprises: receiving an audio signal comprising speech; performing a biometric process on a first part of the audio signal, wherein the first part of the audio signal extends over a first time period; obtaining a speaker recognition score from the biometric process for the first part of the audio signal; performing a biometric process on a plurality of second parts of the audio signal, wherein the second parts of the audio signal are successive sections of the first part of the audio signal, and wherein each second part of the audio signal extends over a second time period and the second time period is shorter than the first time period; obtaining a respective speaker recognition score from the biometric process for each second part of the audio signal; and determining whether there has been a speaker change based on the respective speaker recognition scores for successive second parts of the audio signal.

Abstract: A method of speaker recognition comprises: receiving an audio signal comprising speech; performing a biometric process on a first part of the audio signal, wherein the first part of the audio signal extends over a first time period; obtaining a speaker recognition score from the biometric process for the first part of the audio signal; performing a biometric process on a plurality of second parts of the audio signal, wherein the second parts of the audio signal are successive sections of the first part of the audio signal, and wherein each second part of the audio signal extends over a second time period and the second time period is shorter than the first time period; obtaining a respective speaker recognition score from the biometric process for each second part of the audio signal; and determining whether there has been a speaker change based on the respective speaker recognition scores for successive second parts of the audio signal.

Abstract: Methods and systems for authenticating a user are described. In some embodiments, a series of voice interactions are received from a user during a voiceline session. Each of the voice interactions in the series of voice interaction may be analyzed as each of the voice interactions are received. A confidence level in a verification of an identity of the user may be determined based on the analysis of each of the voice interactions. An access level for the user may be automatically updated based on the confidence level of the verification of the identity of the user after each of the voice interactions is received.

Abstract: A system that incorporates the subject disclosure may perform, for example, receiving a baseline credential and an external credential, mapping the external credential to the baseline credential in a secure element memory, receiving a request for an authentication from a secure device processor of the communication device where the request for the authentication includes a user credential inputted into the communication device, comparing the user credential with the baseline credential to verify the authentication, and providing the authentication and the external credential to the secure device processor without providing the baseline credential to enable the secure device processor to provide the external credential to an external entity device that is remote from the communication device. Other embodiments are disclosed.

Abstract: A method of speaker recognition comprises receiving an audio signal representing speech. A speaker change detection process is performed on the received audio signal. A trigger phrase detection process is also performed on the received audio signal. On detecting the trigger phrase in the received audio signal, a speaker recognition process is performed on the detected trigger phrase and on any speech preceding the detected trigger phrase and following an immediately preceding speaker change.

Abstract: Embodiments of the invention provide for secure voice authentication through a communication device or access device. Certain embodiments allow for providing a word string to a communication device or authentication device. The communication or authentication device plays a supplemental signal that is unique to a transaction. The communication device or authentication device concurrently records an audio segment originating from the user and the supplemental signal. The audio segment is an attempt by the user to vocally reproduce the word string. The communication device or authentication device sends the concurrently recorded audio segment and supplemental signal, to a computer, where the computer authenticates the user.

Abstract: A computer-implemented method for verifying cardholder authenticity when provisioning a token is provided. The method uses an authentication server system having a processor and a memory. The method includes receiving, by the processor, a payment card account identifier provided by a payment requestor. The payment card account identifier for identifying a payment account associated with a cardholder. The method also includes determining a plurality of authentication data associated with the payment requestor, and performing an authentication process using the plurality of authentication data. The authentication process is configured to determine if the payment requestor is the cardholder. The method further includes determining an assurance level associated with the authentication process. The assurance level represents a level of confidence in the authentication process.

Abstract: Methods and systems for authenticating a user are described. In some embodiments, a series of voice interactions are received from a user during a voiceline session. Each of the voice interactions in the series of voice interaction may be analyzed as each of the voice interactions are received. A confidence level in a verification of an identity of the user may be determined based on the analysis of each of the voice interactions. An access level for the user may be automatically updated based on the confidence level of the verification of the identity of the user after each of the voice interactions is received.

Abstract: A cloud client device identifies one or more devices within a predetermined range of the cloud client device operable to communicate with the cloud client device. The cloud client device pairs with one or more of the devices. To provide secure access to the cloud client device and to other functionality provided by the paired devices, the cloud client device accepts tones as a password. The cloud client device receives a password after a prompt as one or more tones and translates the tones for comparison with the password for the cloud client device. Access is allowed if the translated tones match the password for the cloud client device.

Abstract: A method for operating a voice trigger is provided. In some implementations, the method is performed at an electronic device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a sound input. The sound input may correspond to a spoken word or phrase, or a portion thereof. The method includes determining whether at least a portion of the sound input corresponds to a predetermined type of sound, such as a human voice. The method includes, upon a determination that at least a portion of the sound input corresponds to the predetermined type, determining whether the sound input includes predetermined content, such as a predetermined trigger word or phrase. The method also includes, upon a determination that the sound input includes the predetermined content, initiating a speech-based service, such as a voice-based digital assistant.

Abstract: A computer implemented method and system for delegating authority on an online account includes monitoring a user of a plurality of users using an online social network on a communications system. A designated user for an originating user from the plurality of users is assigned, responsive to the originating user of the plurality of user's selection of the designated user. The designated user is activated, responsive to determining an absence of access of the originating user on the online social network. A delegation action is presented to the designated user, and the delegation action is performed on behalf of the originating user, responsive to the designated user's selection of the delegation action.

Abstract: Due to the limited dimension of a NB that may be used by multiple users, as well as possible large coverage areas, timing offset estimation may be outside of NCP. The inaccuracy in the timing estimate can be improved by using more than one tone hopping distance for PRACH. An apparatus may then transmit a first and second tone of the PRACH at a first hopping distance from the first tone. The apparatus may then transmit a third tone of the PRACH and a fourth tone of the PRACH at a second hopping distance from the third tone. The second hopping distance may be greater than first hopping distance. The apparatus may also transmit an additional tone of the PRACH using a random hopping distance. A receiving apparatus may receive the transmitted PRACH and determine a phase estimation based on the sets of tones having different hopping distances.

Abstract: Methods and systems for authenticating a user are described. In some embodiments, a series of voice interactions are received from a user during a voiceline session. Each of the voice interactions in the series of voice interaction may be analyzed as each of the voice interactions are received. A confidence level in a verification of an identity of the user may be determined based on the analysis of each of the voice interactions. An access level for the user may be automatically updated based on the confidence level of the verification of the identity of the user after each of the voice interactions is received.

Abstract: The present application is directed to user authentication confidence based on multiple devices. A user may possess at least one device. The device may determine a device confidence level that the identity of the user is authentic based on at least data collected by a data collection module in the device. For example, a confidence module in the device may receive the data from the data collection module, determine a quality corresponding to the data and determine the device confidence level based on the quality. If the user possesses two or more devices, at least one of the devices may collect device confidence levels from other devices to determine a total confidence level. For example, a device may authenticate the other devices and then receive device confidence levels for use in determining the total confidence level, which may be used to set an operational mode in a device or system.

Abstract: A cloud client device identifies one or more devices within a predetermined range of the cloud client device operable to communicate with the cloud client device. The cloud client device pairs with one or more of the devices. To provide secure access to the cloud client device and to other functionality provided by the paired devices, the cloud client device accepts tones as a password. The cloud client device receives a password after a prompt as one or more tones and translates the tones for comparison with the password for the cloud client device. Access is allowed if the translated tones match the password for the cloud client device.

Abstract: A method for controlling the authorization of a person to access a secure area, particularly a cockpit of a passenger aircraft, is provided. According to the method, an access control apparatus for detecting a set of biometric features is provided, which apparatus can be enabled by entering a predetermined access code. The access code is transferred by the person to the access control apparatus. The access control apparatus detects a set of biometric features of the person transferring the access code. The set of biometric features of the person are saved. Access for the person for a predetermined time period is subsequently enabled. Solely verifying the set of biometric features of the person seeking access allows access to be enabled again for the person during the predetermined time period.

Abstract: Implementations for enabling escalating biometric identification are described. In one example, the method includes receiving a first biometric identification measurement of a person, comparing the first biometric identification measurement of the person with a stored first biometric identification measurement of the person, determining a first confidence level of a match between the first biometric identification measurement of the person and the stored first biometric identification measurement of the person based on the comparing, and determining whether the first confidence level exceeds a first threshold value.

Abstract: An automatic locking system for a medical treatment device helps to ensure that an assistant is present during treatment of a patient. Among the features disclosed biometric authentication to verify that a trained assistant is present, a presence detector to ensure the assistant is continuously present during treatment, and warning and recovery processes that allow intermittent lapses in the continuous presence of the assistant.

Abstract: An arrangement for secure user authentication includes a computer or telecommunication terminal with a smartcard and a device. The smartcard is adapted to securely store biometric information relating to at least one user and the device is adapted to detect biometric data of users. The smartcard and the device include a radio interface for communicating together and a module for exchanging biometric information between each other. In this way, tampering of the transferred biometric information is difficult. In order to increase the security, one or more of the following measures may be used: a secure communication channel between the device and the smartcard, a direct (preferably short range) communication channel between the device and the smartcard and encryption and decryption of biometric information transferred between the device and the smartcard.

Abstract: A method of operating a communication device to interface with a machine system comprises projecting a human-machine interface (HMI) system for the machine system on a surface, wherein the HMI system comprises a plurality of commands associated with the machine system, detecting an input from a user, wherein the input comprises a fluid motion in air performed by the user corresponding to a selection of a command of the plurality of commands associated with the machine system, and transferring the selected command for delivery to the machine system.

Abstract: A method for adaptively tuning a biometric engine comprises the step of generating a database having a plurality of enrollments. Each enrollment corresponds to one or more of a plurality of operation characteristics. The method further comprises the step of comparing, with the biometric engine, enrollments from the database to generate test results including, for each of a plurality of sets of operation characteristics, error rates for a plurality of sensitivity settings and/or confidence score threshold values. The method further comprises the step of analyzing the test results to determine optimized sensitivity settings and/or confidence score threshold values for each set of operation characteristics.

Abstract: A personal digital ID device provides a digital identifier to a service for a predetermined duration in response to user interaction. The user interaction may include a button press. The personal digital ID device may be in the form of a bracelet, a key fob, or other form factor. The service may be provided by a mobile device, in the cloud, or elsewhere.

Abstract: A personal digital ID device provides a digital identifier to a service for a predetermined duration in response to user interaction. The user interaction may include a button press. The personal digital ID device may be in the form of a bracelet, a key fob, or other form factor. The service may be provided by a mobile device, in the cloud, or elsewhere.

Abstract: An apparatus for authenticating a user includes a detector for determining a state or a position of a bodily part placed by the user for biometric authentication, a unit capable of obtaining biometric data from a different portion of the bodily part, a plurality of biometric authentication engines capable of authenticating the user by using one of a plurality of authentication algorithms by comparing the biometric data with reference data, respectively, and a controller for selecting one of the different portions of the bodily part so as to select associated biometric data, and determining one of the biometric authentication engines for authenticating the user on the basis of the state or the position of the bodily part placed.

Abstract: An approach is provided for performing biometric authentication. A determination is made of biometric data from a user equipment having an associated user. Decomposition of the biometric data is caused into one or more closure primitives that represent computation closures of one or more processes of the user equipment. The user is selectively authenticated based on the decomposition of the biometric data.

Abstract: A method is provided for identifying a calling party to a called party utilizing biometric information. Biometric information of first calling party is received. If stored, a calling party profile is retrieved based on first calling party biometric information. A call is placed to a called party. The first calling party profile is provided to called party. A biometric information change from first calling party biometric information to a second calling party biometric information is automatically detected, and it is determined whether the second party biometric information is stored. If stored, a second calling party profile of second calling party is retrieved and is provided to called party. Responsive to determining that the biometric information for second calling party is not stored, the called party is notified that the second calling party is communicating and the second calling party profile is automatically created based on second calling party biometric information.

Abstract: A technique provides authentication codes to authenticate a user to an authentication server. The technique involves generating, by an electronic apparatus (e.g., a smart phone, a tablet, a laptop, etc.), token codes from a cryptographic key. The technique further involves obtaining biometric measurements from a user, and outputting composite passcodes as the authentication codes. The composite passcodes include the token codes and biometric factors based on the biometric measurements. Additionally, the token codes and the biometric factors of the composite passcodes operate as authentication inputs to user authentication operations performed by the authentication server. In some arrangements, the biometric factors are results of facial recognition (e.g., via a camera), voice recognition (e.g., via a microphone), gate recognition (e.g., via an accelerometer), touch recognition and/or typing recognition (e.g., via a touchscreen or keyboard), combinations thereof, etc.

Abstract: There provided an exemplary smart card. The exemplary smart card comprises a microphone for capturing an audio signal. The exemplary smart card also comprises at least one processor for processing the audio signal.

Abstract: The invention is directed to a control system for managing access of users to a plurality of restricted areas. The control system includes at least one manager module and one or more provider modules. The modules are configured in particular fashions.

Abstract: Accessing an automobile with a transponder is disclosed. A processor may determine if the transponder is within range and receive a signal with an identification code from the transponder. If the identification code is valid, user information for the automobile based on the identification code are retrieved. The processor may also process spoken commands if the identification code is valid.

Abstract: Various apparatus, methods, techniques and systems are disclosed for admitting, tracking, monitoring and processing data about visitors and vehicles that visit an access-controlled environment. A network having one or more greeting stations and a number of linked answering stations collects and manages data concerning visitors and/or vehicles in the access-controlled environment, and can manage or assist individuals in managing granting access to the access-controlled environment, monitoring visitors and vehicles present in the access-controlled environment, limiting movement and access to certain areas in the access-controlled environment and generating records and other data about each visit. Some embodiments of the network are also adaptable for use in providing traveler assistance and consular services for various types of individuals.

Abstract: A vehicle screening method and system. A vehicle occupant can be identified utilizing one or more biometric identifiers input by or obtained from the vehicle occupant via a biometric input device. A barcode can also be provided by the vehicle occupant from a scanned card or other structure upon which the barcode is maintained. Additionally, a unique identification number can be provided by the user in order to match the unique identification number against a database of identification numbers, thereby permitting the vehicle occupant to be remotely screened and verified for entry into a secure facility based on the biometric identifier(s), the barcode and the unique identification number.

Abstract: The provenance of passengers intending to depart on a vehicle from a transportation facility, is ensured by providing biometric reading devices at both a check-in station and a departure area station of the facility. The name and/or other information concerning a passenger arriving at the facility is also entered for assessment into a background check system. A biometric template of the passenger is acquired by the reading device at the check-in station and forwarded to the departure area station. When the passenger appears at the latter station, a second biometric template is acquired by the reading device there. The second template is compared with each of a number of templates that were forwarded from the check-in station. If no match exists, or if the background check system returns an unsatisfactory assessment, the passenger is refused boarding onto the vehicle.

Abstract: The invention is directed towards methods, systems and apparatuses, see FIG. 1, (100) for providing secure and private interactions. The invention provides capability for verifying the identity of a party initiating an electronic interaction with another party through data input module (140) which is verified by the identity verification module (150), which further includes a self-destruct mechanism (153). Embodiments of the invention include secure methods for conducting transactions and for limiting the transfer and distribution of personal data to only those data that are absolutely necessary for the completion of the transactions. The invention facilitates the transfer of additional personal data contingent upon an agreement that appropriately compensates the provider of the personal data.

Abstract: Techniques for preventing a driver of a moving vehicle from using a handheld device while driving. An example system of the invention includes a plurality of biometric sensors configured to receive biometric data from the driver and a user of the handheld device. Contemporaneously with operation of the vehicle and the handheld device, the biometric data is analyzed in order to determine a match between the identity of the vehicle driver and the user of the handheld device. A controller is configured to selectively interrupt operation of the vehicle or handheld device upon detecting the match.

Abstract: A system and algorithms to authenticate a person where a system only has some standard personal text data about the person, and cannot have a real biometric template obtained using an enrollment procedure. The authentication allows access to restricted resources by the person. This method is especially useful when it is used as an auxiliary authentication service with other methods such as password or Callback that dramatically lower the chances for an imposter.

Abstract: Systems and methods for providing secure identity authentication amongst devices using identity information contained therein to facilitate data synchronization amongst the user devices, wherein the identity information in the devices are compared for authentication but not actually transmitted or exposed for unauthorized access to such information and to the devices.

Abstract: Conventional techniques for logging and using a user's signature are insecure and inflexible. A system and method are provided which: i) translate a user's first signature, such as a user's voice signature, into a user's second signature, such as a radio frequency identifier signature; and ii) deploy the user's second signature. By translating the user's first signature into the user's second signature and deploying the user's second signature, the provided technique assures the authenticity of the user. Furthermore, the provided system and method enable additional authentication factors, such as a user's personal identification number, to be used with the user's first and second signatures in multiple combinations and sequences to assure the authenticity of the user. As such, the invention provides a security layer offering added security and added flexibility previously unavailable, and which may be applied in a variety of contexts, such as a user device or a retail transaction.

Abstract: A system for confirming that a subject is the source of spoken audio and the identity of the subject providing the spoken audio is described. The system includes at least one motion sensor operable to capture physical motion of at least one articulator that contributes to the production of speech, at least one acoustic signal sensor to receive acoustic signals, and a processing device comprising a memory and communicatively coupled to the at least one motion sensor and the at least one acoustic signal sensor. The processing device is programmed to correlate physical motion data with acoustical signal data to uniquely characterize the subject for purposes of verifying the subject is the source of the acoustical signal data and the identity of the subject.

Abstract: A Bluetooth connection establishment method and system is provided for facilitating establishment of a communication channel between a master device and a target slave device. The method has the steps of broadcasting an inquiry signal for discovering a slave device and transmitting an inquiry response signal. The inquiry response signal is communicated from the slave device to a master device and the inquiry response signal indicates that the inquiry signal has been received by the slave device. The method requests at the master device that the at least one slave device transmits identification information. A slave device list is displayed. An alarm is transmitted by the at least one slave device that received the inquiry signal and a second alarm is transmitted by a target slave device selected from the slave device list in response to an alarm trigger signal transmitted by the master device.

Abstract: A method is provided for identifying a calling party to a called party utilizing biometric information. Biometric information of first calling party is received. If stored, a calling party profile is retrieved based on first calling party biometric information. A call is placed to a called party. The first calling party profile is provided to called party. A biometric information change from first calling party biometric information to a second calling party biometric information is automatically detected, and it is determined whether the second party biometric information is stored. If stored, a second calling party profile of second calling party is retrieved and is provided to called party. Responsive to determining that the biometric information for second calling party is not stored, the called party is notified that the second calling party is communicating and the second calling party profile is automatically created based on second calling party biometric information.

Abstract: A semiconductor element or mobile terminal stores a user's biometric information pattern used for execution of a biometric authentication process and the residual number of trials indicating the number of allowed failures in the biometric authentication process, sends processing data to an external device so that the external device can use the processing data when the external device executes part of the biometric authentication process, and decreases the residual number of trials by a predetermined value while the processing data is output to the external device after start of communication with the external device.

Abstract: A Tradesman's Purchase system is operated by a bank or credit issuing authority that issues a Tradesman's purchasing credit unique ID# to qualifying tradesman selected from the group consisting of plumbers, electricians, carpenters, masons, mechanics, repair shop professionals, contractors, or related construction or trade companies and professions upon payment of an initiation fee and payment of periodic maintenance fees. The unique ID# provides pre-negotiated discount levels for tradesmen within the group contracted with pre-selected wholesalers, jobbers and businesses. The unique ID# is linked to the tradesman's name, business, professional status, license number and biometric data including palm print, finger print, iris print and voice print. Professional purchases by the tradesman are tracked by the system, analyzed and reported to sponsoring manufacturers of goods, jobbers or wholesalers for a fee.

Abstract: A software-based security agent that hooks into the operating system of a computer device in order to continuously audit the behavior and conduct of the end user of the computer device. The detected actions of the end user can be stored in a queue or log file that can be continuously monitored to detect patterns of behavior that may constitute a policy violation and/or security risk. When a pattern of behavior that may constitute a policy violation and/or security risk is detected, an event may be triggered. A frequency vector string matching algorithm also is disclosed. The frequency vector string matching algorithm may be used to detect the presence or partial presence of subject strings within a target string of alphanumeric characters. The frequency vector string matching algorithm could be used to detect typos in stored computer records or to search for records based on partial information.