Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...

MAI-2024-0011

Large Language Models LLMs that incorporate safety protocols such as filtering mechanisms and alignment training are susceptible to information leakage through "Decomposition Attacks." These attacks strategically fragment a malicious query into multiple innocuous sub-queries, prompting the LLM to...