REVIEW 5 cited by
Learning diverse attacks on large language models for robust red-teaming and safety tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts requires discovering diverse attacks. Automated red-teaming typically uses reinforcement learning to fine-tune an attacker language model to generate prompts that elicit undesirable responses from a target LLM, as measured, for example, by an auxiliary toxicity classifier. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. As a flexible and probabilistically principled alternative, we propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts. We find that the attacks generated by our method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer well between target LLMs. Finally, we demonstrate that models safety-tuned using a dataset of red-teaming prompts generated by our method are robust to attacks from other RL-based red-teaming approaches.
Forward citations
Cited by 5 Pith papers
-
LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.
-
From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
Seed2Harvest expands 1,000 human adversarial prompts into 27,650 LLM-generated variants that keep roughly comparable unsafe-image trigger rates and add hundreds of new geographic contexts.
-
Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.
-
Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation
Coordinated misleading text descriptions of video, audio, and meaning flip the appropriateness labels assigned by most multimodal LLMs in about 90% of test videos.
-
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
The submission's abstract promises an LLM safety survey, but the provided body is the opening page of an unrelated arithmetic-dynamics paper, so the artifact is internally inconsistent.
Discussion (0). Sign in to comment.