NRT-Bench reports that adaptive multi-turn attacks cause critical safety function loss in 8.7-12.1% of sessions across four frontier LLM operator models, with nearly disjoint vulnerabilities and strongly model-dependent defense effects.
Multi-turn context jailbreak attack on large language models from first principles
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
years
2026 4representative citing papers
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.
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.
A multi-role red-teaming framework with attacker, target, and jury LLMs measures faithfulness in English and Arabic, finding false-premise prompts and length limits change unfaithfulness rates.
citing papers explorer
-
NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms
NRT-Bench reports that adaptive multi-turn attacks cause critical safety function loss in 8.7-12.1% of sessions across four frontier LLM operator models, with nearly disjoint vulnerabilities and strongly model-dependent defense effects.
-
SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
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.
-
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.
-
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
A multi-role red-teaming framework with attacker, target, and jury LLMs measures faithfulness in English and Arabic, finding false-premise prompts and length limits change unfaithfulness rates.