InfoNewsLLM-specific
Cisco Open Sources Quarry to Catch AI Agent Attacks Hidden in Harmless Steps
- Published
- Record updated
Summary
Cisco open sourced Project Quarry, a neurosymbolic rule language that combines ML classifiers and LLM judges with symbolic checks to detect AI agent attacks spread across sequences of individually benign actions. It covers LLM conversations, agents, tool use, MCP interactions, and multimodal inputs, and integrates with Cisco's Integrated AI Security & Safety Framework. The article cites 2025 Claude Code campaigns against about 30 organizations and Mexican government institutions as examples of split, routine-looking attacks.