Research · curated 18 Jul 2026
ICML Poster MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
First reported icml.cc
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
MultiBreak targets multi-turn jailbreaks, a harder-to-defend class of attacks against deployed LLMs, giving defenders a way to systematically measure model resilience beyond single-prompt tests.
MultiBreak, presented as an ICML 2026 poster by Jialin Song and colleagues, is described as a scalable and diverse multi-turn jailbreak benchmark for evaluating LLM safety. The poster page provides only a truncated abstract, but frames the work as a benchmark contribution for measuring how models withstand multi-turn jailbreak attacks.