SLIP enables self-jailbreaking of aligned LLMs via lexical insertion in breadth-first tree search, reaching 94.7% average ASR on AdvBench and HarmBench across eleven models with ~7.9 calls.
arXiv preprint arXiv:2404.16369 (2024)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
polarities
background 2representative citing papers
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
SSAG bypasses logit suppression in five LLMs to produce harmful responses at 95% success rate and 86% lower latency; VulMine reaches 77% attack success against defenses.
THREAT uses coordinated LLMs in an iterative optimization loop to generate jailbreak prompts that achieve higher success rates and lower detection rates than previous methods across tested models and datasets.
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
citing papers explorer
-
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
SLIP enables self-jailbreaking of aligned LLMs via lexical insertion in breadth-first tree search, reaching 94.7% average ASR on AdvBench and HarmBench across eleven models with ~7.9 calls.
-
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
-
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
SSAG bypasses logit suppression in five LLMs to produce harmful responses at 95% success rate and 86% lower latency; VulMine reaches 77% attack success against defenses.
-
Adversarial Reframing: A Framework for Targeted Generation in Language Models
THREAT uses coordinated LLMs in an iterative optimization loop to generate jailbreak prompts that achieve higher success rates and lower detection rates than previous methods across tested models and datasets.
-
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.