REVIEW 7 cited by
Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
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
Signed reviews
read the original abstract
Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In light of this, the field of red teaming is undergoing fast-paced growth, highlighting the need for a comprehensive survey covering the entire pipeline and addressing emerging topics. Our extensive survey, which examines over 120 papers, introduces a taxonomy of fine-grained attack strategies grounded in the inherent capabilities of language models. Additionally, we have developed the "searcher" framework to unify various automatic red teaming approaches. Moreover, our survey covers novel areas including multimodal attacks and defenses, risks around LLM-based agents, overkill of harmless queries, and the balance between harmlessness and helpfulness.
Forward citations
Cited by 7 Pith papers
-
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
RAG can make language models less safe than their non-RAG equivalents, even with safe documents, and current jailbreak methods transfer poorly to RAG.
-
Adaptively Robust LLM Monitoring via Activation Watermarking
Activation Watermarking embeds a secret keyed direction in an LLM's hidden states so policy-violating responses can be detected by a cosine test, cutting adaptive-jailbreak evasion relative to guard models.
-
The Automation Advantage in AI Red Teaming
Automated LLM red-teaming achieves higher success rates than manual prompting (69.5% vs 47.6%) but manual solves are faster when they succeed, according to 214,271 attack attempts on the Crucible platform.
-
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Model tampering attacks, especially few-shot fine-tuning, reliably re-elicit unlearned capabilities in Llama-3-8B and can bound the success of held-out input-space attacks.
-
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.
-
A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
A three-phase taxonomy of physical risk control for foundation-model-enabled robots, with identified research gaps.
-
Prompt Optimization and Evaluation for LLM Automated Red Teaming
Applying Attack Success Rate to individual attacks via repeated testing yields an ASR distribution that, when used to mine contrastive pairs, improves automated red-teaming prompt optimization over single-try ASR.
Discussion (0). Continue with ORCID to comment.