A clustering-based stateful online monitor detects distributed multi-agent cyberattacks that evade standard per-transcript monitors, catching them 30% earlier in large-scale simulated traffic with low overhead.
arXiv preprint arXiv:2402.16914 (2024)
10 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
10
Pith papers citing it
3
external citations · external index
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
background 1representative citing papers
HMNS is a new jailbreak method that uses causal head identification and nullspace-constrained injection to achieve higher attack success rates than prior techniques on aligned language models.
MTK detects jailbreaks by monitoring the evolution of prompt neighborhood structures on the data manifold through LLM layers, reporting 95% TPR at 5% FPR on benign and 2% on pseudo-malicious prompts plus 85% TPR under adaptive attacks.
Babel is an efficient black-box jailbreaking framework that formalizes sparse safety attention heads via a mathematical obfuscation model and uses iterative distribution refinement to achieve higher attack success rates on models like GPT-4o and Claude-3-5-haiku with around 40 queries.
SelfGrader grades query harmfulness from anchored numerical-token logits plus PAC-guided dual-perspective ICL, claiming strong jailbreak detection with low FPR and latency.
Develops the BSD data generation pipeline and two new datasets to evaluate decomposition attacks as effective misuse enablers and stateful defenses as a countermeasure in language model safety.
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.
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.
GUARD automates generation of guideline-violating questions and jailbreak diagnostics to test LLM compliance with government ethics guidelines, validated empirically on eight models and extended to vision-language models.
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
citing papers explorer
-
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.