Bengio et al. — 2026 International AI Safety Report: AI-powered cyberattacks and safety-testing evasion 2026-02-03 Research
UCSC / The Register — CHAI: physical prompt injection hijacks self-driving cars and drones via road signs 2026-02-03 Research
arXiv — AgentDoG: a diagnostic guardrail framework for AI agent safety and security 2026-02-02 Research
arXiv — The Promptware Kill Chain: reframing prompt injection as multi-step malware 2026-02-02 Research
arXiv — SENTINEL: securing AI agents in cyber-physical systems against deepfake and MCP-mediated attacks 2026-02-02 Research
Clutch Security — 95% of enterprise MCP servers run on endpoints with zero security visibility 2026-02-02 Security
GitGuardian / NHIcon 2026 — Agentic AI forces a paradigm shift in non-human identity security 2026-02-02 Security
InstaTunnel — Agent hijacking and intent breaking: the goal-oriented attack surface 2026-02-02 Security
Keyfactor — Two-thirds of enterprises say AI agents are a bigger security risk than humans 2026-02-02 Security
Christian Schneider — From LLM to agentic AI: how agents amplify prompt injection into kill chains 2026-02-02 Security
Check Point / Lakera — 40% of 10,000 MCP servers found to have security weaknesses 2026-02-01 Security