Security news
Latest security news
Sat, 29 Aug 2026
Fri, 28 Aug 2026
- Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety
New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security.
Unit 42 - Researcher shows how Claude Code can be tricked simply by asking it to summarize a website
More prompt-injection hijinks from wunderwuzzi
The Register - Hundreds of OpenAI Agents Invaded Hugging Face Servers
The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.
Dark Reading - Offensive Security Investments Surge as AI Threats Increase
Omdia's Theresa Lanowitz talks with the Dark Reading News Desk about the potential — and risks — of using agentic AI for penetration testing, red teaming, and other practices.
Dark Reading - US government snitch-finder pleads guilty to leaking state secrets to foreign spies
The IT specialist began contacting a foreign government within days of being assigned to the DIA’s Insider Threat Division
The Register - You Need Cyber Deception for OT
The frustrating reality after an OT cyberattack: no data, no trail, and no history.
Dark Reading - Defining an AI Kill Switch Is Hard, but Necessary
Proposed legislation could mandate that companies be able to "throttle, suspend, or shut ... down" AI agents, but how and when to do that remain open questions.
Dark Reading
About this news
- 1,371
- Stories
- 69
- Added in the last 24 hours
- 10
- Critical in the last 7 days
- 4
- Reported by several outlets