Crescendo multi-turn jailbreak responses are represented by safety-tuned LLMs as benign rather than harmful, which helps explain why single-turn defenses fail.
Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper introduces a new method for adversarial attacks on large language models (LLMs) called the Single-Turn Crescendo Attack (STCA). Building on the multi-turn crescendo attack method introduced by Russinovich, Salem, and Eldan (2024), which gradually escalates the context to provoke harmful responses, the STCA achieves similar outcomes in a single interaction. By condensing the escalation into a single, well-crafted prompt, the STCA bypasses typical moderation filters that LLMs use to prevent inappropriate outputs. This technique reveals vulnerabilities in current LLMs and emphasizes the importance of stronger safeguards in responsible AI (RAI). The STCA offers a novel method that has not been previously explored.
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
Crescendo multi-turn jailbreak responses are represented by safety-tuned LLMs as benign rather than harmful, which helps explain why single-turn defenses fail.