Abstract: Methods and systems are described for developing a malicious content detector to identify new malicious text content, such as phishing messages, malicious documents, and/or malicious web content. A computing device is used to generate input data which contains an instruction, examples of content, and content to be analyzed. The examples include malicious and benign content samples, designed to recognize similar malicious content. The computing device feeds this input into a generative language model, which produces text labels that indicate the maliciousness of the content to be analyzed. The methods and systems enable rapid development of security protection by leveraging a small number of malicious samples, instead of training with a large dataset of new training samples.

Abstract: A compute instance stores a programmable feature extractor associated with a machine learning model maintained by a server-based computing system configured to communicate with the compute instance by way of a network. The machine learning model is based on a feature set that includes a plurality of features. The compute instance executes the programmable feature extractor to generate a feature vector corresponding to a data instance accessed by the compute instance, where the feature vector includes a feature value specific to the data instance for each feature included in the feature set. The compute instance transmits the feature vector corresponding to the data instance to the server-based computing system for use as a training input to the machine learning model.

Abstract: An automated system attempts to characterize code as safe or unsafe. For intermediate code samples not placed with sufficient confidence in either category, human-readable analysis is automatically generated to assist a human reviewer in reaching a final disposition. For example, a random forest over human-interpretable features may be created and used to identify suspicious features in a manner that is understandable to, and actionable by, a human reviewer. Similarly, a k-nearest neighbor algorithm may be used to identify similar samples of known safe and unsafe code based on a model for, e.g., a file path, a URL, an executable, and so forth. Similar code may then be displayed (with other information) to a user for evaluation in a user interface. This comparative information can improve the speed and accuracy of human interventions by providing richer context for human review of potential threats.

Abstract: An apparatus for detecting malicious files includes a memory and a processor communicatively coupled to the memory. The processor receives multiple potentially malicious files. A first potentially malicious file has a first file format, and a second potentially malicious file has a second file format different than the first file format. The processor extracts a first set of strings from the first potentially malicious file, and extracts a second set of strings from the second potentially malicious file. First and second feature vectors are defined based on lengths of each string from the associated set of strings. The processor provides the first feature vector as an input to a machine learning model to produce a maliciousness classification of the first potentially malicious file, and provides the second feature vector as an input to the machine learning model to produce a maliciousness classification of the second potentially malicious file.

Abstract: A computer implemented method of a secure computing component to provide access to a cryptographic key, the key being associated with the secure component by a digitally signed record in a blockchain wherein the blockchain is accessible via a network and includes a plurality of records validated by miner computing components, the method including receiving a request from another secure computing component to associate the key with the other component, the request having associated identification information for a requester of the key; responsive to a verification of an entitlement of the requester, generating a new record for storage in the blockchain, the new record associating the key with the other component and being validated by the miner components; and further responsive to the verification, securely transferring the key to the other component so as to provide access to the key to the key requester via the other component.

Abstract: A computer-implemented method and system for authorizing user access to services provided by a first entity is disclosed. The method involves receiving a request to authorize a user, retrieving a plurality of user-related metrics from a database, generating a risk metric based on these metrics, and automatically determining the user's authorization based on the risk metric. The authorization decision involves a second entity assuming a portion of the risk for the services provided by the first entity and the first entity assuming a second portion of the risk for the services. The method further includes communicating the authorization decision to a graphical user interface, providing a clear indication of the user's authorized access.

Abstract: A computer-implemented method of processing audio data, the method comprising receiving input audio data (x) comprising a time-series of amplitude values; transforming the input audio data (x) into an input frequency band decomposition (X1) of the input audio data (x); transforming the input frequency band decomposition (X1) into a first latent representation (Z); processing the first latent representation (Z) by a first deep neural network to obtain a second latent representation (Z{circumflex over (?)}, Z1{circumflex over (?)}); transforming the second latent representation (Z{circumflex over (?)}, Z1{circumflex over (?)}) to obtain a discrete approximation (X3{circumflex over (?)}); element-wise multiplying the discrete approximation (X3{circumflex over (?)}) and a residual feature map (R, X5{circumflex over (?)}) to obtain a modified feature map, wherein the residual feature map (R, X5{circumflex over (?)}) is derived from the input frequency band decomposition (X1); processing a pre-shaped frequency band

Abstract: An article of footwear includes an upper, a sole structure coupled to the upper, at least one receiver integrated into an exterior surface of the upper, and a removable shield configured to selectively attach to the at least one receiver. The removable shield has an outward-facing ornamental exterior surface when attached to the at least one receiver.

Abstract: In some embodiments, a processor receives, via an interface, natural language data associated with a user request for performing an identified computational task associated with a cybersecurity management system. The processor is configured to provide the natural language data as input to a machine learning (ML) model. The ML model is configured to automatically infer a template query based on the natural language data. The processor is further configured to cause the template query to be displayed, via the interface. The processor is further configured to receive, via the interface, user input indicating a finalized query associated with the identified computational task, and to provide the finalized query as input to a system configured to perform the identified computational task. The processor is further configured to modify a security setting in the cybersecurity management system based on the performance of the identified computational task.

Abstract: In some embodiments, a method includes processing at least a portion of a received file into a first set of fragments and analyzing each fragment from the first set of fragments using a machine learning model to identify within each fragment first information potentially relevant to whether the file is malicious. The method includes forming a second set of fragments by combining adjacent fragments from the first set of fragments and analyzing each fragment from the second set of fragments using the machine learning model to identify second information potentially relevant to whether the file is malicious. The method includes identifying the file as malicious based on the first information within at least one fragment from the first set of fragments and the second information within at least one fragment from the second set of fragments. The method includes performing a remedial action based on identifying the file as malicious.

Abstract: A virtual machine (VM) test instance is created in a virtual machine scale set. When the VM test instance is created, a unique set of credentials is also created corresponding to the VM test instance. The unique set of credentials is stored in a secret store that is separate from other cloud and organization credentials. When access to a VM test instance is requested by a user, the unique credentials are provided to the user to use the VM test instance for a limited time. When the user is finished using the VM test instance, or when the VM test instance expires, then the VM test instance is destroyed and the unique credentials are also destroyed.

Abstract: In one or more embodiments, a command is repeatedly input a predetermined number of times into a machine learning model to generate a plurality of different natural language (NL) descriptions. The plurality of different NL descriptions are input into the machine learning model to generate a plurality of different check commands. A plurality of similarity metrics are determined by comparing each check command from the plurality of different check commands to the command. A check command from the plurality of different check commands that is most similar to the command is identified based on the plurality of similarity metrics. An NL description from the plurality of different NL descriptions is caused to be displayed, the NL description previously input into the machine learning model to generate the check command.

Abstract: A battery module includes features to optimize cooling while providing electrical isolation and cell gas-venting channels. The battery module can include the integration of a heatsink in order to improve thermal performance. Thermally conductive pads can be provided to create an electrically isolated interface between a plurality of series-connected battery-cell lead plates, at different potentials, and the heatsink. Optimization, by stacking thin and thick thermally conductive pads, allows for creation of gas-venting channels along the positive cell terminal locations. In some arrangements, a plurality of fluid paths are disposed between the inlet and the outlet of the battery module to provide heat convective airflow through the battery module.

Abstract: A memory device can include a first portion having a memory array comprising a plurality of memory cells and a first via chain segment for performing a test operation. The memory device can include a second portion comprising processing circuitry and a second via chain segment for performing the test operation. The memory device can also include an interconnect coupling the first portion and the second portion, the interconnect comprising a third via chain segment, wherein the first via chain segment, second via chain segment, and third via chain segment can be selected independently.

Abstract: In some embodiments, a processor can receive an input string associated with a potentially malicious artifact and convert each character in the input string into a vector of values to define a character matrix. The processor can apply a convolution matrix to a first window of the character matrix to define a first subscore, apply the convolution matrix to a second window of the character matrix to define a second subscore and combine the first subscore and the second subscore to define a score for the convolution matrix. The processor can provide the score for the convolution matrix as an input to a machine learning threat model, identify the potentially malicious artifact as malicious based on an output of the machine learning threat model, and perform a remedial action on the potentially malicious artifact based on identifying the potentially malicious artifact as malicious.

Abstract: A method for inserting a wire. An image of a connector is generated using a camera system connected to an end effector. The end effector is at a connector pose facing the connector. A region in the image encompassing the connector is selected. An initial mask is created using the image and the region. The initial mask comprises a background region and a connector region. A segmentation mask is created using the initial mask and the image, wherein the segmentation mask includes edges for the connector. Thresholding is applied to the segmentation mask to recover pixels for the connector and generate a final mask. The final mask is used to insert the wire into the connector.

Abstract: The present invention relates to methods and compositions for treating autoimmune or inflammatory disease characterised by an aberrant or inappropriate immune response to one or more of Ro60 protein; MPO protein; and Smith protein.

Abstract: A spray system includes a spray device with a housing enclosing an electrostatic power supply that generates an electrostatic charging voltage and a nozzle assembly including a liquid tip that receives a spray liquid and an air stream and emits an atomized spray and an electrode coupled to receive the electrostatic charging voltage and configured to inductively charge the spray. A base unit includes a liquid source that supplies the spray liquid, an air source that supplies the air stream and a power source that supplies power for the electrostatic power supply. A tether couples the spray device to the base unit. The tether includes a liquid supply line coupling the liquid source to the liquid tip, an air supply line coupling the air source to the liquid tip, and a power supply line coupling the power source to the electrostatic power supply.

Abstract: In some embodiments, a processor receives natural language data for performing an identified cybersecurity task. The processor can provide the natural language data to a first machine learning (ML) model. The first ML model can automatically infer a template query based on the natural language data. The processor can receive user input indicating a finalized query and to provide the finalized query as input to a system configured to perform the identified computational task. The processor can provide the finalized query as a reference phrase to a second ML model, the second ML model configured to generate a set of natural language phrases similar to the reference phrase. The processor can generate supplemental training data using the set of natural language phrases similar to the reference phrase to augment training data used to improve performance of the first ML model and/or the second ML model.