A method of computer authentication of a user request for a Subscriber Identity Module (SIM) card transfer by a biometric signature from a user equipment (UE) comprising assigning a risk score, by a mobile service provider, to a user account based on user activity in the user account, wherein the user activity includes a SIM card transfer authorization. The mobile service provider then sends a message requesting a biometric signature from an authentication application executing in memory on the UE. The authentication application on the UE then proceeds capturing a biometric signature, encrypting the biometric signature, and sending an encrypted biometric signature to the mobile service provider using a wireless communication protocol. The mobile service provider then compares the biometric signature to an authorized signature and modifies the risk score based on the comparison.

A method of computer authentication of a user request for a Subscriber Identity Module (SIM) card transfer by a biometric signature from a user equipment (UE) comprising assigning a risk score, by a mobile service provider, to a user account based on user activity in the user account, wherein the user activity includes a SIM card transfer authorization. The mobile service provider then sends a message requesting a biometric signature from an authentication application executing in memory on the UE. The authentication application on the UE then proceeds capturing a biometric signature, encrypting the biometric signature, and sending an encrypted biometric signature to the mobile service provider using a wireless communication protocol. The mobile service provider then compares the biometric signature to an authorized signature and modifies the risk score based on the comparison.

A system and method for batched, supervised, in-situ machine learning classifier retraining for malware identification and model heterogeneity. The method produces a parent classifier model in one location and providing it to one or more in-situ retraining system or systems in a different location or locations, adjudicates the class determination of the parent classifier over the plurality of the samples evaluated by the in-situ retraining system or systems, determines a minimum number of adjudicated samples required to initiate the in-situ retraining process, creates a new training and test set using samples from one or more in-situ systems, blends a feature vector representation of the in-situ training and test sets with a feature vector representation of the parent training and test sets, conducts machine learning over the blended training set, evaluates the new and parent models using the blended test set and additional unlabeled samples, and elects whether to replace the parent classifier with the retrained version.

The present disclosure describes systems and methods for determining a subsequent action of a simulated phishing campaign. A campaign controller identifies a starting action for a simulated phishing campaign directed to a user of a plurality of users. The simulated phishing campaign includes a plurality of actions, one or more of the plurality of actions to be determined during execution of the simulated phishing campaign The campaign controller responsive to the starting action, communicates a simulated phishing communication to one or more devices of a user. The campaign controller determines a subsequent action of the plurality of actions of the simulated phishing campaign based at least on one of a response to the simulated phishing communication received by the campaign controller or a lack of response within a predetermined time period and initiating, responsive to the determination, the subsequent action of the simulated phishing campaign.

According to an example aspect of the present invention, there is provided an apparatus comprising a first part (110) which comprises a first light-based communication port (114) and a network interface (112), a second part (120) which comprises a non-volatile memory (122) and a second light-based communication port (124), and wherein the apparatus is configured to deactivate at least one of the first light-based communication port (114) and the second light-based communication port (124) responsive to determining that a read or write operation in the non-volatile memory (122) is complete.

An abnormal traffic analysis apparatus includes receiving means for receiving traffic from a device, analysis means for analyzing whether or not traffic received from the device is abnormal traffic, analysis result recording means for recording a result of analysis performed by the analysis means, and device management means for managing movement of the device between edges. If it is determined by the device management means that a device that is a target of analysis performed by the analysis means moves to an edge, the receiving means creates information for continuing analysis of traffic received from the device and transmits the information to an apparatus for analyzing traffic that is included in the edge to which the device moves.

An abnormal traffic analysis apparatus includes receiving means for receiving traffic from a device, analysis means for analyzing whether or not traffic received from the device is abnormal traffic, analysis result recording means for recording a result of analysis performed by the analysis means, and device management means for managing movement of the device between edges. If it is determined by the device management means that a device that is a target of analysis performed by the analysis means moves to an edge, the receiving means creates information for continuing analysis of traffic received from the device and transmits the information to an apparatus for analyzing traffic that is included in the edge to which the device moves.

According to some embodiments, a system, method and non-transitory computer-readable medium are provided to protect a cyber-physical system having a plurality of monitoring nodes comprising: a normal space data source storing, for each of the plurality of monitoring nodes, a series of normal monitoring node values over time that represent normal operation of the cyber-physical system; a situational awareness module including an abnormal data generation platform, wherein the abnormal data generation platform is operative to generate abnormal data to represent abnormal operation of the cyber-physical system using values in the normal space data source and a generative model; a memory for storing program instructions; and a situational awareness processor, coupled to the memory, and in communication with the situational awareness module and operative to execute the program instructions to: receive a data signal, wherein the received data signal is an aggregation of data signals received from one or more of the plurality of monitoring nodes, wherein the data signal includes at least one real-time stream of data source signal values that represent a current operation of the cyber-physical system; determine, via a trained classifier, whether the received data signal is a normal signal or an abnormal signal, wherein the trained classifier is trained with the generated abnormal data and normal data; localize an origin of an anomaly when it is determined the received data signal is the abnormal signal; receive the determination and localization at a resilient estimator module; execute the resilient estimator module to generate a state estimation for the cyber-physical system. Numerous other aspects are provided.

According to some embodiments, a system, method and non-transitory computer-readable medium are provided to protect a cyber-physical system having a plurality of monitoring nodes comprising: a normal space data source storing, for each of the plurality of monitoring nodes, a series of normal monitoring node values over time that represent normal operation of the cyber-physical system; a situational awareness module including an abnormal data generation platform, wherein the abnormal data generation platform is operative to generate abnormal data to represent abnormal operation of the cyber-physical system using values in the normal space data source and a generative model; a memory for storing program instructions; and a situational awareness processor, coupled to the memory, and in communication with the situational awareness module and operative to execute the program instructions to: receive a data signal, wherein the received data signal is an aggregation of data signals received from one or more of the plurality of monitoring nodes, wherein the data signal includes at least one real-time stream of data source signal values that represent a current operation of the cyber-physical system; determine, via a trained classifier, whether the received data signal is a normal signal or an abnormal signal, wherein the trained classifier is trained with the generated abnormal data and normal data; localize an origin of an anomaly when it is determined the received data signal is the abnormal signal; receive the determination and localization at a resilient estimator module; execute the resilient estimator module to generate a state estimation for the cyber-physical system. Numerous other aspects are provided.

A request for a confidential web page, and in response, can transmit an HTML code snippet to a browser running on a network device coupled to the data communication network to determine whether JavaScript is enabled locally at the network device. The confidential web page can be, for example, a log in, or other sensitive or personal data, vulnerable to browser-based intrusions. Responsive to detecting that JavaScript has been disabled, restricts subsequent communication by the network device, wherein the application firewall requires enabling of JavaScript to continue to the confidential web page. On the other hand, responsive to detecting that JavaScript has not been disabled, allowing the request for the confidential web page to proceed.