HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks