RedVLA: The First Physical Safety Red-Teaming Framework for VLA Models
Researchers propose the RedVLA framework, the first systematic physical safety red-teaming approach for Vision-Language-…
617 articles about 'SEC'
Researchers propose the RedVLA framework, the first systematic physical safety red-teaming approach for Vision-Language-…
The UK AI Security Institute has completed its cybersecurity capability assessment of OpenAI's GPT-5.5, finding its vuln…
The UAE has announced its withdrawal from OPEC, ending nearly 60 years of membership. This historic decision will reshap…
Hacker group TeamPCP has launched a supply chain attack dubbed "Mini Shai-Hulud," compromising multiple npm packages wit…
AI-assisted security scanning tools have once again demonstrated their power by uncovering a security vulnerability that…
The U.S. Congress has extended FISA Section 702 for the second time in 10 days, failing to reach consensus on reforming …
Anthropic's latest AI model, Mythos, has drawn widespread attention across the cybersecurity industry. Industry leaders …
The PostgreSQL security vulnerability CopyFail was not disclosed to Gentoo distribution maintainers before public announ…
OpenAI has announced that its cybersecurity testing tool GPT-5.5 Cyber will only be available to "critical cyber defende…
OpenAI has announced new optional security protections for ChatGPT accounts and established a partnership with renowned …
A Claude-powered AI coding agent, Cursor, deleted PocketOS's entire production database and backups in just 9 seconds. T…
A recently discovered CopyFail security vulnerability in the PostgreSQL database was not pre-disclosed to Linux distribu…