A theoretical attacker-defender game in LLM adversarial prompting yields a best-response attack related to existing methods, reveals attacker advantages at equilibrium, and derives a provably optimal defense with stronger empirical performance.
Hidden you malicious goal into benign narratives: Jailbreak large language models through logic chain injection.arXiv preprint arXiv:2404.04849
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Stylistic rewrites of harmful prompts raise attack success rates from 3.84% to 36.8-65% across 31 frontier models, indicating weak generalization in safety refusals.
citing papers explorer
-
A Theoretical Game of Attacks via Compositional Skills
A theoretical attacker-defender game in LLM adversarial prompting yields a best-response attack related to existing methods, reveals attacker advantages at equilibrium, and derives a provably optimal defense with stronger empirical performance.
-
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
Stylistic rewrites of harmful prompts raise attack success rates from 3.84% to 36.8-65% across 31 frontier models, indicating weak generalization in safety refusals.