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.
GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
background 1representative citing papers
DRTO improves LLM consistency on reasoning tasks under distribution shifts by 4.4 points on MATH-500 and 2.7 points on LiveCodeBench via f-divergence ambiguity sets in token-level RLHF.
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
Develops a taxonomy of security interaction levels in AI/cloud infrastructure and demonstrates practical attacks exploiting isolation assumptions.
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
citing papers explorer
-
Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
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.
-
Distributionally Robust Token Optimization in RLHF
DRTO improves LLM consistency on reasoning tasks under distribution shifts by 4.4 points on MATH-500 and 2.7 points on LiveCodeBench via f-divergence ambiguity sets in token-level RLHF.
-
SafeAgent: A Runtime Protection Architecture for Agentic Systems
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
-
Investigating The Security of Modern AI and Cloud Infrastructure
Develops a taxonomy of security interaction levels in AI/cloud infrastructure and demonstrates practical attacks exploiting isolation assumptions.
-
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.