Dormant face-recognition code reportedly appeared in Meta’s smart glasses app, then disappeared after scrutiny. That has put Meta’s AI eyewear plans back under the privacy spotlight.
GitHub confirmed on May 20 that a poisoned VS Code extension installed on an employee’s device gave attackers access to roughly 3,800 internal repositories at the Microsoft-owned code storage and ...
A max-severity vulnerability in the latest Python FastAPI version of the ChromaDB project allows unauthenticated attackers to run arbitrary code on exposed servers. The flaw is tracked as ...
A malicious Hugging Face repository managed to take a spot in the platform's trending list by impersonating OpenAI's Privacy Filter open-weight model to deliver a ...
Abstract: Software vulnerabilities pose significant security threats to modern systems, particularly those involving complex execution sequences and intricate call relationships across multiple ...
Threat actors are testing malware that incorporates large language models (LLMs) to create malware that can evade detection by security tools. In an analysis published earlier this month, Google's ...
Detection as code (DaC) is a powerful way for security teams to streamline rule development, automate threat detection, and respond to attacks with greater speed and precision. The DaC approach ...
Attackers are finding more and more ways to post malicious projects to Hugging Face and other repositories for open source artificial intelligence (AI) models, while dodging the sites' security checks ...
Cybersecurity researchers have uncovered two malicious machine learning (ML) models on Hugging Face that leveraged an unusual technique of "broken" pickle files to evade detection. "The pickle files ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results