security
security
more in this beat
- jun 04securityChatGPT's New Lockdown Mode Borrows Apple's Name for a Prompt-Injection Kill Switch
- jun 04securityStored Prompt Injection Now Persists Across AI Agent Sessions
- jun 04securityLLM Data Poisoning Survives the Data-Cleaning Defenses Built to Stop It
- jun 01securityWhy Attack Success Rate Misleads LLM Jailbreak Benchmarks
- may 27securityOpenAI's New Safety Bug Bounty Pays Researchers for Jailbreaks and Policy Bypasses
- may 23securityAI Jailbreaks Are Now a Reasoning Problem, Not a Prompt Problem
- may 18securityTrustFall: One Keypress in Claude Code, Gemini CLI, Cursor, and Copilot CLI Triggers Unsandboxed RCE
- may 18securityMultiBreak Benchmark: 10,389 Multi-Turn Jailbreak Prompts Raise ASR 54pp on DeepSeek-R1-7B
- apr 29securityInstructLab CVE-2026-6859: Hardcoded trust_remote_code=True Turns Any HuggingFace Model Into RCE
- apr 29securityMercor's 4TB Lapsus$ Breach Hands Voice-Clone Attackers 40,000 Pre-Verified Targets
- apr 24securityCitizen Lab's 'Bad Connection' Names Three Telecom Entry Points, Shows Diameter Silently Falls Back to SS7
- apr 23securityMarch-April MCP CVEs Expose the Local-Host Trust Model in AI Agent Frameworks
- feb 20securityThe Mysterious Case of Chinese Bot Traffic in 2026: How AI-Powered Bots Are Rewriting the Rules of Detection