Strata-Sword organizes jailbreak attacks into three reasoning-complexity levels and shows that LLMs' safety failure rates rise with attack complexity, especially for new Chinese-language attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions
Strata-Sword organizes jailbreak attacks into three reasoning-complexity levels and shows that LLMs' safety failure rates rise with attack complexity, especially for new Chinese-language attacks.