International Business Machines Corporation

Nec Corporation

Konstantin Levinski

Tien Hiong Lee

Weng Sing Tang

Harjoben Singh

Chee Meng Low

Liang Zhu

Xin Qu

Xin Qian

Iskandar Goh

Edwin Boaz Soenaryo

Xiang Zhang

Randy V Kamajaya

Wei Liang Chua

Christopher G Fredericks

Methods, systems and computer readable medium for liveness detection authentication of a facial image are provided. The method includes acquiring a first image of the facial image illuminated with a first color, acquiring a second image of the facial image illuminated with a second color, and determining if the facial image is consistent with a three-dimensional (3D) structure in response to a combination of the first and second images. The method further includes authenticating the facial image if the facial image is consistent with a 3D structure and the facial image matches a face of user to be authenticated.

Method and system for chrominance-based face liveness detection

A mechanism is provided for secure sensitive private information dependent transactions. A query and a transaction token S associated with a current transaction between a SPI owner and the service provider is received. Particular SPI required is identified based on the query. A request for the particular SPI from the SPI owner is constructed thereby forming a constructed request. The constructed request is sent to one or more authorized devices associated with the SPI owner enrolled with the cognitive SPI broker. The particular SPI is received from a device of the SPI owner thereby forming received SPI. The received SPI is used complete the transaction. A notification is then sent to the SPI owner that the transaction has been completed.

Secure sensitive personal information dependent transactions

A method, system and a computer program product are provided for updating mobile device applications at a central cloud server by establishing an application virtual machine representation of a first mobile device application installed on a mobile device; updating the application virtual machine representation at the central cloud server to perform software configuration, installation, upgrade, optimization, testing, or maintenance tasks on the application virtual machine representation without using computational resources at the mobile device; and sending the mobile device one or more modules that were changed when updating the application virtual machine representation for integration into the first mobile device application installed on the mobile device.

Method and system for mobile applications update in the cloud

The method includes identifying a log stream from a first device, wherein the first device is of an unknown device type. The method further includes identifying features in the log stream from the first device. The method further includes determining a probability that the log stream from the first device was created by a specific device type based on matching of features of the identified log stream from the first device and features in log streams from a plurality of known device types.

Fingerprinting and matching log streams

A log entry identifies an error in the computer or other system. Another log entry identifies a symptom associated with the system error. The symptom occurs in timeframe prior to the system error and a variable score is determined for the symptom according to the timeframe, the consistency with which the symptom appears along with the error, and the frequency with which the symptom occurs throughout the system log. A new occurrence of the symptom is identified. Whether the symptom's variable score exceeds a threshold value for the symptom is determined. In response to determining that the symptom's variable score exceeds the threshold value, an alert indicating that the associated system error is probable is displayed.

Probabilistic prediction of software failure

A mechanism is provided for detecting one or more defects in an incoming log. One or more features are extracted from the incoming log. Utilizing the one or more features, one or more patterns, one or more pattern sequences of the one or more patterns, and one or more proximities associated with the one or more patterns contained in the incoming log are identified. For each defect model generated for the incoming log, a set of patterns in the defect model is compared to a set of patterns in each previously identified defect model in a set of previously identified defect models. Responsive to identifying a match and responsive to set of scores associated with the match meeting or exceeding a set of probability thresholds, an identification associated with the previously identified defect model along with any solution or workaround is passed to a support engineer.

Probabilistic detect identification

A computer-implemented method includes receiving one or more log files. Each of the one or more log files includes one or more logs. The computer-implemented method further includes extracting one or more event records from said one or more logs. The computer-implemented method further includes, for each event record of the one or more event records, determining one or more attributes and one or more dimensions based on the event record, respectively. The computer-implemented method further includes grouping the one or more event records into one or more attribute groups. The computer-implemented method further includes ordering the one or more event records of each of the one or more attribute groups by the one or more dimensions. The computer-implemented method further includes generating one or more graphical representations of the one or more attribute groups. A corresponding computer system and computer program product are also disclosed.

Visualization of graphical representation of log files

Embodiments of the present invention disclose populating a database by conducting a training phase to analyze training security log streams. A server extracts the words contained within the training security log and replaces each of the extracted words with a symbol to form a symbol string and an n-gram scan is conducted on the symbol string to generate statistical data. Tokens are extracted from symbol string, where the tokens are words, phrase or alphanumeric sequence represented by a symbol within training security log stream. The symbol string is replaced with the words they represent to allow for the identification of the actual token phrases. A scan is conducted on the token phrase to acquire scan data on the identified token phrases. Once the tokens, position information, and scan data are known they are stored within the database to allow security log streams to be analyzed in real time.

System and method for field extraction of data contained within a log stream

A first plurality of traffic data transmitted by a first client device associated with a first vehicle may be received. The received first plurality of traffic data may be stored in a database according to a license plate of the first vehicle. A second plurality of traffic data transmitted by a second client device associated with a second vehicle may be received. The license plate of the first vehicle may be identified within the received second plurality of traffic data using at least one image recognition technique. The identified license plate may be determined to be stored in the database. The first plurality of traffic data may be transmitted to the second client device based on determining the identified license plate is stored in the database. The transmitted first plurality of traffic data may be displayed within a user interface associated with the second client device.

Growing community of inventors

Singapore, Singapore

Konstantin Levinski