task · first seen 6 Oct 2026
multi-agent system security
Protecting LLM-based multi-agent systems against adversarial inputs, tool misuse, and malicious delegation.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems SecurityPapers · 6 Oct 2026 · Shaswata Mitra, Raj Patel, Subash Neupane, Sudip Mittal, Md Rayhanur Rahman, Sha…
- An Exploration of Attacks on AI Agent SystemsPapers · 8 Oct 2026 · Cathleen Qiao, Layah Vigneaud, Chloe Brandon, Max Cabilangan, Xiyuan Cao, Isaac…
- ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent SystemsPapers · 8 Nov 2026 · Riya Bharathwaj, Akshara Prabhakar, Roshan Ram, Avni Kothari, Sarah Tan, Huan Wa…
Latest sources
- ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent SystemsPapers · 8 Nov 2026 · Riya Bharathwaj, Akshara Prabhakar, Roshan Ram, Avni Kothari, Sarah Tan, Huan Wa…
- An Exploration of Attacks on AI Agent SystemsPapers · 8 Oct 2026 · Cathleen Qiao, Layah Vigneaud, Chloe Brandon, Max Cabilangan, Xiyuan Cao, Isaac…
- Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems SecurityPapers · 6 Oct 2026 · Shaswata Mitra, Raj Patel, Subash Neupane, Sudip Mittal, Md Rayhanur Rahman, Sha…