Abstract: A node associated with an organization may receive a storage identifier for new credit data associated with an individual. A distributed ledger and distributed data sources may be used to share the new credit data with a network of nodes. The node may update a smart contract with the storage identifier for the new credit data. The node may receive, from a particular device associated with the organization, a request for the new credit data. The node may obtain the storage identifier for the new credit data from the smart contract. The node may obtain the new credit data by using the storage identifier to search the distributed data sources. The node may provide the new credit data to the particular device. The node may perform actions to obtain additional new credit data from the distributed data sources or provide the additional new credit data to the distributed data sources.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.

Abstract: An apparatus includes a processor, persistent memory coupled to the processor, and a memory protection logic. The processor may include multiple processing engines. The persistent memory may include a persistent storage portion and a memory expansion portion. The memory protection logic is to: obtain a first ephemeral component associated with the persistent storage portion; generate a persistent key using the first ephemeral component; obtain a second ephemeral component associated with the memory expansion portion; and generate a non-persistent key using the second ephemeral component. Other embodiments are described and claimed.

Abstract: A system for link device authentication includes a computing device configured to acquire, from an originating device, an identifier of an endpoint device, obtain an endpoint device authentication code corresponding to the identifier, determine, as a function of the identifier, a location of the endpoint device, identify a plurality of link devices, select, from the plurality of link devices, at least a probabilistically verified link device as a function of the location of the endpoint device, and transmit, to the at least a probabilistically verified link device, the endpoint device authentication code.

Abstract: In a transportation security technique, images are stored that are received from image capturing equipment deployed at respective screening nodes. The images are analyzed using a machine learning model, where presence of a particular object in an image indicates that a threat condition exists at the screening node. The analyzed images are transmitted to threat assessment components in accordance with predetermined criteria. An indication that the particular object is observed in the image is received from the threat assessment components. An indication that the particular object is observed in the image is transmitted to the screening node responsive to receiving the indication that the particular object is observed in the image. An indication of whether the particular object is present at the screening node is received. The machine learning model is trained based on the received indication of whether the particular object is observed in the image.

Abstract: The disclosed techniques in artificial intelligence include at least a system and a computer-implemented method for performing a predictive search that compensates for a misclassification. For example, the system can set a user-defined classification of a physical characteristic of the user and retrieve an image captured by a camera device. The system can aggregate binary feedback data submitted by authorized users about the image, predict a classification for the physical characteristic by processing the image with a machine learning (ML) process, and search a database based on a query, which has criteria that includes an indication of the aggregate binary feedback data, the user-defined classification, the predicted classification, and/or data indicative of the user's feedback. The system can then identify a search result that satisfies the query and cause a user device to display a recommendation that includes the search result.

Abstract: A system and method for accelerated anomaly detection and replacement of an anomaly-experiencing machine learning-based ensemble includes identifying a machine learning-based digital threat scoring ensemble having an anomalous drift behavior in digital threat score inferences computed by the machine learning-based digital threat scoring ensemble for a target period; executing a tiered anomaly evaluation for the machine learning-based digital threat scoring ensemble that includes identifying at least one errant machine learning-based model of the machine learning-based digital threat scoring ensemble contributing to the anomalous drift behavior, and identifying at least one errant feature variable of the at least one machine learning-based model contributing to the anomalous drift behavior; generating a successor machine learning-based digital threat scoring ensemble to the machine learning-based digital threat scoring ensemble based on the tiered anomaly evaluation; and replacing the machine learning-based di

Abstract: An apparatus has a network interface circuit providing connectivity to a network with network connected client machines hosting email client modules controlling email inboxes. A processor is connected to the network interface circuit. A memory is connected to the processor. The memory stores instructions executed by the processor to scan the email inboxes to identify statistically infrequently received emails from different network connected service providers. Protocols utilized by the different network connected service providers to accept user data delete requests are identified. The protocols are executed.

Abstract: The present disclosure relates to a computer-implemented method and an apparatus for classifying anomalies of one or more feature-associated anomalies in network data traffic between devices in a first part of a network and devices in a second part of the network. The method comprises retrieving at least one network data traffic sample and determining one or more feature-associated anomaly scores for the retrieved at least one network data traffic sample. The method further comprises determining feature importance of each feature of a feature-associated anomaly score and classifying one or more anomalies based on the determined one or more feature-associated anomaly scores and the determined feature importance.

Abstract: A security platform employs a variety techniques and mechanisms to detect security related anomalies and threats in a computer network environment. The security platform is “big data” driven and employs machine learning to perform security analytics. The security platform performs user/entity behavioral analytics (UEBA) to detect the security related anomalies and threats, regardless of whether such anomalies/threats were previously known. The security platform can include both real-time and batch paths/modes for detecting anomalies and threats. By visually presenting analytical results scored with risk ratings and supporting evidence, the security platform enables network security administrators to respond to a detected anomaly or threat, and to take action promptly.

Abstract: Embodiments for a method of tracking provenance information for data in a database are disclosed. The method includes storing data in a first one or more cells of a database, translating provenance information for the data into a new block for a provenance blockchain corresponding to the first one or more cells, and storing the new block in the database.

Abstract: A malware infection prediction method predicts a likelihood that a client device is to be infected with in a period of time based on state and behavior telemetry data. A malware infection prediction system receives telemetry data associated with use (i.e. behavior data) and configuration (i.e. state data) of a client device. By using a trained model, the system predicts a likelihood of the client device becoming infected within a given time frame. Based on the predicted likelihood, the system generates recommendations including recommended actions for reducing the likelihood of the client device becoming infected. The system then generates notifications including the recommendations and sends the notifications to the client device or to an administrative account associated with the client device.

Abstract: Provided is a method including: associating a virtual display of an object with first media content including a first type media content; associating the virtual display of the object with second media content that includes second type media content; generating a data model that includes the virtual display associated with the first media content and the second media content; and storing the data model in a storage device coupled to the computer system. As such, the method unifies all components (e.g., media content, tags, permissions, descriptions) of the data model—text description and attributes, image, video, and audio—to create a unique, multi-dimensional, transferable digital representation of an idea, memory, or history tied to the object.

Abstract: Machine learning methods and systems for developing security governance recommendations are disclosed.

Abstract: Various embodiments are directed to systems and methods for encryption key management within a group-based communication platform.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to facilitate information exchange using publish-subscribe with blockchain. An example apparatus includes a security manager to integrate a security service with an instruction execution flow in a distributed device environment. The security manager is to include a processor. The processor is to be configured to implement at least an executable hierarchical state machine to provide credential management and access management in conjunction with instruction execution according to an execution plan. The executable hierarchical state machine is to generate a security context for the execution plan to implement a guard condition governing a transition from a first state to a second state in accordance with the execution plan.

Abstract: Techniques for providing privacy features in communication systems are provided. For example, a message may be provided from user equipment to an element or function in a communication network that comprises one or more privacy indicators, where privacy features for processing the message are determined based on the privacy indicators. The message may comprise an attach request comprising a subscription identifier for a subscriber associated with the user equipment, with the privacy indicators comprising a flag indicating whether the subscription identifier in the attach request is privacy-protected. As another example, the element of function in the communication network may determine privacy features supported by the communication network and generate and send a message to user equipment comprising one or more privacy indicators selected based on the determined privacy features.

Abstract: A digital object architecture infrastructure includes a handle system that stores handle data and a proxy server that caches handle data for rapid access. A client connects to the proxy server to request access to the handle data. When the handle data does not have access restrictions and is currently cached, the proxy server returns the handle data to the client without accessing the handle system. When the handle data does not have access restrictions and is not cached, the proxy server obtains the handle data from the handle system, caches a copy of the handle data for future access, and provides the handle data to the client. The proxy server may cache encrypted handle data that is subject to access restrictions, cannot be decrypted by proxy server, and can be provided to a client determined to be allowed access. The client can then decrypt the encrypted handle data.

Abstract: The present teaching generally relates to providing optimized access control rules. A request may be received from a client device. A determination may be made, based on the request, that an update is needed for access control rule information for the client device. Rule data may be generated. The rule data may include a plurality of data buckets each including one or more access control rules, each data bucket of the plurality being associated with a range of destination port numbers, and where each of the one or more access control rules comprise a set of tuples having a common source network and source port number, and one or more destination port numbers associated with the common source network and source port number. The rule data may be sent to the client device.

Abstract: Techniques for providing Internet of Things (IoT) security are disclosed. An applicable system includes profiling IoT devices to limit the number of network signatures applicable to the IoT devices and performing pattern matching using a pattern that is appropriate for the profile of a given IoT device.