Patent classifications
G06F21/57
Systems and methods for verifying a watermark of an AI model for a data processing accelerator
Embodiments of the disclosure relate to verifying a watermark of an artificial intelligence (AI) model for a data processing (DP) accelerator. In one embodiment, a system receives an inference request from an application. The system extracts the watermark from an AI model having the watermark. The system verifies the extracted watermark based on a policy. The system applies the AI model having a watermark to a set of inference inputs to generate inference results. The system sends a verification proof and the inference results to the application.
Subsystem for configuration, security, and management of an adaptive system
An integrated circuit (IC) can include a processor system configured to execute program code, a programmable logic, and a platform management controller coupled to the processor system and the programmable logic. The platform management controller is adapted to configure and control the processor system and the programmable logic independently.
Maximization of side-channel sensitivity for trojan detection
An exemplary method of detecting a Trojan circuit in an integrated circuit is related to applying a test pattern comprising an initial test pattern followed by a corresponding succeeding test pattern to a golden design of the integrated circuit, wherein a change in the test pattern increases side-channel sensitivity; measuring a side-channel parameter in the golden design of the integrated circuit after application of the test pattern; applying the test pattern to a design of the integrated circuit under test; measuring the side-channel parameter in the design of the integrated circuit under test after application of the test pattern; and determining a Trojan circuit to be present in the integrated circuit under test when the measured side-channel parameters vary by a threshold.
Maximization of side-channel sensitivity for trojan detection
An exemplary method of detecting a Trojan circuit in an integrated circuit is related to applying a test pattern comprising an initial test pattern followed by a corresponding succeeding test pattern to a golden design of the integrated circuit, wherein a change in the test pattern increases side-channel sensitivity; measuring a side-channel parameter in the golden design of the integrated circuit after application of the test pattern; applying the test pattern to a design of the integrated circuit under test; measuring the side-channel parameter in the design of the integrated circuit under test after application of the test pattern; and determining a Trojan circuit to be present in the integrated circuit under test when the measured side-channel parameters vary by a threshold.
Building a package dependencies data structure
A system, product and process for building a package dependencies data structure. The method comprises determining a package instance identifier of the package to be processed. The package instance identifier is determined based on a unique identifier of the package to be processed and based on a unique identifier of a dependency sub-tree of the package to be processed in the package instance identifier. The package instance identifier is utilized to determine if a node representing the package to be processed exists or not. In case the node does not exist already in the data structure, the node is created and added.
Computer-implemented method of security-related control or configuration of a digital system
A computer-implemented method includes: receiving system information data representing configurations of digital systems; receiving attack information data associated one or more of the digital systems; analyzing the received system information data and attack information data, to associated attack types; identifying, for each identified attack type, correlations and/or causalities between individual system constituents or combinations thereof in the digital systems associated with attacks; determining and assigning, based on the identified correlations and/or causalities, an attack vulnerability value, for each attack, respectively, to each of the systems and/or systems' constituents and/or combinations thereof; and retrievably storing attack vulnerability values associated with the systems, system constituents and/or combinations thereof.
Technologies for providing shared memory for accelerator sleds
Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.
Technologies for providing shared memory for accelerator sleds
Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.
ATTACK INFORMATION PROCESSING APPARATUS, ATTACK INFORMATION PROCESSING METHOD, AND COMPUTER READABLE MEDIUM
An attack information processing apparatus (10) includes an extraction unit (11) configured to extract first and second attack knowledge pieces indicating conditions of a cyber attack from first and second attack information pieces including descriptions of the cyber attack, a determination unit (12) configured to determine similarity between the first and second attack information pieces, and a complementing unit (13) configured to complement the first attack knowledge piece with the second attack knowledge piece based on the determined similarity.
DEPLOYING A SYSTEM-SPECIFIC SECRET IN A HIGHLY RESILIENT COMPUTER SYSTEM
A computer-implemented method for providing a system-specific secret to a computing system having a plurality of computing components is disclosed. The method includes storing permanently a component-specific import key as part of a computing component and storing the component-specific import key in a manufacturing-side storage system. Upon a request for the system-specific secret for a computing system, the method includes identifying the computing component comprised in the computing system, retrieving a record relating to the identified computing component, determining the system-specific secret protected by a hardware security module and determining a system-specific auxiliary key. Furthermore, the method includes encrypting the system-specific auxiliary key with the retrieved component-specific import key, thereby creating a auxiliary key bundle, encrypting the system-specific secret and storing the auxiliary key bundle and a system record in a storage medium of the computing system.