Abstract: Techniques for providing data loss prevention, including data exfiltration prevention and crypto-ransomware prevention, are provided. In some embodiments, a slack-space file system is created by using a modified packing algorithm to increase and/or optimize an amount of slack space created by files stored in a standard file system. A program for accessing and indexing the slack-space file system may be stored, and requests by a user to store data on a storage medium of a computer system may cause the information to be stored in the slack-space file system, where it may be protected from destructive malware that operates solely on the standard file system. In some embodiments, sensitive information may be hidden by storing the information in an alternate data stream of a file and by replacing the information in the unnamed data stream of the file with non-sensitive information that may appear to be sensitive.

Abstract: Techniques for detecting anomalies in multispectral image data, and more specifically for detecting presentation attacks by using multispectral image data in biometric security applications, are provided. In some embodiments, a system may receive multispectral image data and generate an estimation of a first image of a plurality of images of the multispectral image data, wherein the estimation is based on other images of the multispectral image data, but not the first image itself. The estimation may then be compared to the first image to generate an indication as to whether the multispectral image data represents a presentation attack. In some embodiments, a system may receive multispectral training image data and may extract features from the data to generate and store a network architecture for predicting relationships of multispectral images of subjects.

Abstract: Provided are asynchronous data ingestion and enrichment systems and methods. The systems comprise a plurality of components (e.g., ingestion components, enrichment components, and/or publishing components). Instead of passing data from one component to another, the data is sent to a messaging queue that formats and hold the data until the subsequent component is ready to receive it. Additionally, each component comprises a central microservice and a plurality of instances, the central microservice configured to communicate with each instance of the plurality of instances.

Abstract: Techniques for providing network security and anomaly detection are disclosed. In some embodiments, network traffic may be monitored in order to create a model of network traffic over a first period of time. Based on the model of network traffic, one or more inflated files may be created and stored on a system, wherein the inflated files are of a sufficient file size such that attempts to exfiltrate one or more of the files may be detected based by network monitoring tools. The inflated files may further include one or more indicators of sensitivity, including indicators of the presence of sensitive information that is not actually included in the inflated files. Network traffic characteristics may then be repeatedly or continuously monitored in order to update the size of the one or more inflated files based on changes in network traffic characteristics.

Abstract: Techniques for providing data loss prevention, including data exfiltration prevention and crypto-ransomware prevention, are provided. In some embodiments, a slack-space file system is created by using a modified packing algorithm to increase and/or optimize an amount of slack space created by files stored in a standard file system. A program for accessing and indexing the slack-space file system may be stored, and requests by a user to store data on a storage medium of a computer system may cause the information to be stored in the slack-space file system, where it may be protected from destructive malware that operates solely on the standard file system. In some embodiments, sensitive information may be hidden by storing the information in an alternate data stream of a file and by replacing the information in the unnamed data stream of the file with non-sensitive information that may appear to be sensitive.

Abstract: Techniques for authenticating a mobile user device at a base station of a mobile network, and more specifically for implementing a distributed ledger based authentication that is shared by multiple base stations of the mobile network is provided. In one or more examples, the base stations of a mobile network can act as nodes in a distributed ledger system. A mobile device seeking to gain access to the mobile network can be provided a distributed ledger identification number by a base station. The distributed ledger identification number can be converted to a block of the distributed ledger, and then transmitted to the other base stations (i.e., nodes) that maintain the same distributed ledger. The mobile device can subsequently use the distributed ledger identification number for future access requests at either the same base station, or any of the other base stations that maintain the same distributed ledger.

Abstract: Techniques for determining whether a nucleic acid sequence is genetically engineered are provided. In some embodiments, a ratio is calculated based on a number of input reads that align with reference data, and the ratio is inputted into a classifier to determine whether the input reads represent an engineered sequence. In some embodiments, first output data is generated based on unassembled read-based comparison of nucleic acid data, while second output data is generated based on assembly-based comparison of the nucleic acid data; the first and second output data are inputted into a classifier to determine whether the input data represents an engineered sequence. In some embodiments, nucleic acid data is compared to three reference datasets representing (i) engineered sequences, (ii) evolutionary variations of an organism, and (iii) evolutionary variations of other organisms; a determination as to whether the input data represents an engineered sequence is based on the three comparisons.

Abstract: Disclosed herein are systems and methods for optimizing air traffic control managing using a Quantum Annealing-based iterative path planning technique and algorithm that involves both classical and quantum computation components. The classical component can calculate the distances between aircraft and the target destination from a set of new, possible properties, such as aircraft location. The quantum component can select from the new, possible properties to minimize the distance of the aircraft to the target destination while ensuring adequate separation between aircraft. The algorithm can utilize qubits to represent maneuverability options for aircraft. The maneuverability options may be partitioned into a set of multiple qubits per aircraft. Each set may include a plurality of qubits that are representative of the sub options. The algorithm can utilize Quadratic Unconstrained Boolean Optimization (QUBO) to find the lowest cost-energy maneuverability option.

Abstract: Techniques for determining whether a public encryption key is vulnerable as the result of deficiencies in pseudorandom number generation algorithms are provided. In some embodiments, a system may compile a database of cryptographic information received from a plurality of sources, including databases, and network traffic monitoring tools. RSA public keys extracted from the cryptographic information may be stored in an organized database in association with corresponding metadata. The system may construct a product tree from all unique collected RSA keys, and may then construct a remainder tree from the product tree, wherein each output remainder may be determined to be a greatest common divisor of one of the RSA keys against all other unique RSA keys in the database. The system may then use the greatest common divisors to factor one or more of the RSA keys and to determine that the factored keys are vulnerable to being compromised.

Abstract: Techniques for authenticating a mobile user device at a base station of a mobile network, and more specifically for implementing a distributed ledger based authentication that is shared by multiple base stations of the mobile network is provided. In one or more examples, the base stations of a mobile network can act as nodes in a distributed ledger system. A mobile device seeking to gain access to the mobile network can be provided a distributed ledger identification number by a base station. The distributed ledger identification number can be converted to a block of the distributed ledger, and then transmitted to the other base stations (i.e., nodes) that maintain the same distributed ledger. The mobile device can subsequently use the distributed ledger identification number for future access requests at either the same base station, or any of the other base stations that maintain the same distributed ledger.

Abstract: An adversarial reinforcement learning system is used to simulate a security checkpoint. The system includes a simulation engine configured to simulate a security checkpoint and various threat objects and threat-mitigation objects therein. The system further includes an attack model configured to control threat objects in the simulation and a defense model configured to control threat-mitigation objects in the simulation. A first portion of the simulation is executed by the simulation engine in order to generate an outcome of the first portion of the simulation. The defense model then generates a threat-mitigation input to control threat-mitigation objects in a subsequent portion of the simulation, and the attack model then generates a threat input to control threat objects in the subsequent portion of the simulation, wherein the inputs are based in part on the outcome of the first portion of the simulation.

Abstract: The present disclosure is directed to data classification. An exemplary computer-enabled method for classifying image data comprises: receiving an input image patch, wherein the input image patch is of a second data domain; providing the input image patch to a preprocessing algorithm to obtain a preprocessed image patch, wherein the preprocessing algorithm is trained to transform data of the second data domain to data of a first data domain; providing the preprocessed image patch to a pre-trained classification algorithm, wherein the pre-trained classification algorithm is trained based on training data of the first data domain; obtaining one or more classification outputs from the pre-trained classification algorithm based on the preprocessed image patch.

Abstract: Techniques for authenticating a mobile user device at a base station of a mobile network, and more specifically for implementing a distributed ledger based authentication that is shared by multiple base stations of the mobile network is provided. In one or more examples, the base stations of a mobile network can act as nodes in a distributed ledger system. A mobile device seeking to gain access to the mobile network can be provided a distributed ledger identification number by a base station. The distributed ledger identification number can be converted to a block of the distributed ledger, and then transmitted to the other base stations (i.e., nodes) that maintain the same distributed ledger. The mobile device can subsequently use the distributed ledger identification number for future access requests at either the same base station, or any of the other base stations that maintain the same distributed ledger.

Abstract: Systems and methods are provided for performing automated face recognition and comparison. An input image of a face may be received and cropped, and the image may be processed through a deep neural network (DNN) to produce a k-dimensional feature vector. The k-dimensional feature vector may be converted to a k-dimensional binary vector by transforming each value in the vector to either 1 or 0. To search for nearest matches of the image in a database of gallery images of faces, the system may compare sub-strings of the binary vector to hash tables created from sub-strings of the gallery images, enabling sub-linear searching that allows locating the closest matches from among the entire gallery without requiring an exhaustive linear search of the entire gallery.

Abstract: Systems and methods for performing genomic information compression, transmission, and decompression are provided. A system for compression, transmission, and decompression of genomic information includes a first computer associated with a first index and a second computer associated with a second index, each index containing reference permutations of nucleic acid sequence portions, each permutation associated with a reference number. The first computer uses input genomic information and the first index to produce a compressed representation of the genomic information, and transmits the compressed representation to the second computer. The second computer uses the compressed representation and the second index to assemble a data representation of the genomic information. The compressed representation comprises references to permutations, indications of locations of each permutation in the input information, indications of variations to permutations, and/or indications of sequence length.

Abstract: Disclosed herein are systems and methods for simulating an environment over a plurality of intervals of in-simulation time by using a two-part data structure to represent agents or entities in the simulation. A system may create and store a data structure representing an agent in the simulation, wherein a first portion of the data structure represents characteristics of the agent at a present interval and a second portion of data structure represents characteristics of the agent at a future interval of the simulation. Also disclosed herein are systems and methods for executing a multi-agent simulation using multiple processing threads. A system may group a plurality of agents in the simulated environment into subsets associated respectively with nodes of the simulated environment, assign the subsets to respective separate processors of the system, and execute the simulation using separate processing threads associated respectively with the separate processors.

Abstract: Disclosed herein are systems and methods for collectively optimizing cooperative actions among autonomous connected vehicles. A system may include a plurality of autonomous connected machines and/or vehicles that may establish a mesh network for communication amongst one another. Remote from the mesh network, the system may include a consortium configured to communicate with the mesh network, such as by cellular communication. The mesh network of connected vehicles may collectively receive, from the remote consortium, reliability information associated with the autonomous vehicles in the mesh network, and may collectively generate a shared map of the environment surrounding the plurality of autonomous connected vehicles in accordance with the reliability information. Based on the shared map, the mesh network of connected vehicles may collaboratively generate a collective navigation plan for the plurality of vehicles to navigate the environment.

Abstract: Described are systems and methods for using a network-control application to dynamically reconfigure a Software Defined Networking (SDN) in response to detected internal or external events. The network-control application can receive, via an SDN controller, an operational status of the SDN network to determine whether a user-configured policy is applicable and should be applied on the SDN network. The network-control application can receive, via one or more data sources external to the SDN network, information including an event and a geographical indicator to determine whether a user-configured policy is applicable and should be applied on the SDN network. Once a policy is selected, the network-control application can be configured to generate and transmit a command to the SDN controller to cause the SDN controller to reconfigure the SDN network in accordance with the policy. Therefore, the SDN network may be preemptively reconfigured before severe degradation occurs.

Abstract: Techniques for allocating memory on non-volatile storage mediums, rather than on RAM storage mediums, are provided. In some embodiments, first functions in program code for allocating memory on RAM storage are replaced with corresponding second functions for allocating memory on non-volatile storage. Library files corresponding to the second functions may be stored in programming language libraries, such that the second function may be defined in order to allocate memory on non-volatile storage. In some embodiments, a library file for allocating memory on RAM storage may be modified such that it instead causes allocation of memory on non-volatile storage. Allocating memory, storing data in memory, or retrieving data in memory may, in some embodiments, include providing instructions for a processor to communicate via a bus associated with non-volatile storage rather than a bus associated with RAM storage.

Abstract: Systems and methods are provided for performing automated face recognition and comparison. An input image of a face may be received and cropped, and the image may be processed through a deep neural network (DNN) to produce a k-dimensional feature vector. The k-dimensional feature vector may be converted to a k-dimensional binary vector by transforming each value in the vector to either 1 or 0. To search for nearest matches of the image in a database of gallery images of faces, the system may compare sub-strings of the binary vector to hash tables created from sub-strings of the gallery images, enabling sub-linear searching that allows locating the closest matches from among the entire gallery without requiring an exhaustive linear search of the entire gallery.