VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
Mrj-agent: An effective jailbreak agent for multi-round dialogue
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 4representative citing papers
MultiBreak is a large diverse multi-turn jailbreak benchmark that achieves substantially higher attack success rates on LLMs than prior datasets and reveals topic-specific vulnerabilities in multi-turn settings.
Domain contexts blur LLM safety boundaries, enabling the Jargon attack framework to exceed 93% success on seven frontier models via safety-research contexts and multi-turn interactions, with a policy-guided mitigation.
The paper taxonomizes jailbreak attacks and defenses for LLMs, introduces the Security Cube multi-dimensional evaluation framework, benchmarks 13 attacks and 5 defenses, and identifies open challenges in LLM robustness.
citing papers explorer
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
-
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
MultiBreak is a large diverse multi-turn jailbreak benchmark that achieves substantially higher attack success rates on LLMs than prior datasets and reveals topic-specific vulnerabilities in multi-turn settings.
-
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
Domain contexts blur LLM safety boundaries, enabling the Jargon attack framework to exceed 93% success on seven frontier models via safety-research contexts and multi-turn interactions, with a policy-guided mitigation.
-
SoK: Robustness in Large Language Models against Jailbreak Attacks
The paper taxonomizes jailbreak attacks and defenses for LLMs, introduces the Security Cube multi-dimensional evaluation framework, benchmarks 13 attacks and 5 defenses, and identifies open challenges in LLM robustness.