GovInfoSecurity

Flaw in AI Libraries Exposes Models to Remote Code Execution

Researchers discovered remote code execution vulnerabilities in three AI libraries from Apple, Salesforce and Nvidia used by ...

Python libraries used in top AI and ML tools hacked

Security researchers from Palo Alto Networks have discovered vulnerabilities used in some top Artificial Intelligence (AI) ...
GitHub

MITRE ATT&CK® Data Model

The ATT&CK Data Model (ADM) provides a type-safe, object-oriented interface for working with MITRE ATT&CK datasets. Built on STIX 2.1 compliance, it uses Zod schemas and TypeScript types to ensure ...
IEEE

BAUODNET for Class Imbalance Learning in Underwater Object Detection

Abstract: Underwater object detection is of great significance for various applications in underwater scenes. However, class imbalance issue is still an unsolved bottleneck for current underwater ...
IEEE

Not All Classes are Equal: Adaptively Focus-Aware Confidence for Semi-Supervised Object Detection

Abstract: Semi-supervised object detection (SSOD) is a significant application of Semi-supervised learning to further improve object detectors but suffers more ...
GitHub

High-fidelity 3D Human Digitization from Single 2K Resolution Images (2K2K)

Part-wise Normal Prediction divides an image into each body part through a matrix using keypoints. This helps in predicting detailed normal vectors for each body part with minimal computation.