SRTJ is a training-free jailbreak method that evolves hierarchical attack rules using iterative verifier feedback and ASP-based constraint-aware composition to achieve stable high success rates on HarmBench across multiple LLMs.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
years
2026 6representative citing papers
PrecisionDiff is a differential testing framework that uncovers widespread precision-induced behavioral disagreements in aligned LLMs, including safety-critical jailbreak divergences across precision formats.
An attention-guided RL reward combined with diverse persuasion strategies produces higher attack success rates against large reasoning models than prior jailbreak methods.
JBShield is vulnerable to adaptive JB-GCG attacks (up to 53% ASR) because jailbreak representations occupy a distinct region in refusal-direction space; the new RTV defense using Mahalanobis detection on multi-layer fingerprints reaches 0.99 AUROC and limits adaptive ASR to 7%.
FLP uses multi-persona foresight simulation to detect infections via response diversity and applies local purification to reduce maximum cumulative infection rates in multi-agent systems from over 95% to below 5.47%.
TEMPLATEFUZZ mutates chat templates with element-level rules and heuristic search to reach 98.2% average jailbreak success rate on twelve open-source LLMs while degrading accuracy by only 1.1%.
citing papers explorer
-
Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements
PrecisionDiff is a differential testing framework that uncovers widespread precision-induced behavioral disagreements in aligned LLMs, including safety-critical jailbreak divergences across precision formats.
-
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
An attention-guided RL reward combined with diverse persuasion strategies produces higher attack success rates against large reasoning models than prior jailbreak methods.
-
Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems
FLP uses multi-persona foresight simulation to detect infections via response diversity and applies local purification to reduce maximum cumulative infection rates in multi-agent systems from over 95% to below 5.47%.