Combines LTL formal methods with LLMs for auditing, predictive monitoring, and runtime intervention on temporally extended behavioral constraints, outperforming LLM baselines and reducing violations.
Openai’s approach to external red teaming for ai models and systems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
FlashRT delivers 2x-7x speedup and 2x-4x GPU memory reduction for prompt injection and knowledge corruption attacks on long-context LLMs versus nanoGCG.
AVISE provides a new framework and automated SET that identifies jailbreak vulnerabilities in language models with 92% accuracy, finding all nine tested models vulnerable to an augmented Red Queen attack.
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
citing papers explorer
-
Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
Combines LTL formal methods with LLMs for auditing, predictive monitoring, and runtime intervention on temporally extended behavioral constraints, outperforming LLM baselines and reducing violations.
-
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
FlashRT delivers 2x-7x speedup and 2x-4x GPU memory reduction for prompt injection and knowledge corruption attacks on long-context LLMs versus nanoGCG.
-
AVISE: Framework for Evaluating the Security of AI Systems
AVISE provides a new framework and automated SET that identifies jailbreak vulnerabilities in language models with 92% accuracy, finding all nine tested models vulnerable to an augmented Red Queen attack.
-
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts
Red-Bandit adapts online to LLM failure modes by dynamically selecting among RL-trained LoRA attack-style experts via a bandit policy, reporting SOTA ASR@10 on AdvBench with lower-perplexity prompts.
-
FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.