Across multiple jailbreak methods and models, the model's attention to the unsafe request drops during a successful attack, and a temperature-based attention sharpening defense counters this at zero overhead.
Token highlighter: Inspecting and mitigating jailbreak prompts for large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
Across multiple jailbreak methods and models, the model's attention to the unsafe request drops during a successful attack, and a temperature-based attention sharpening defense counters this at zero overhead.