The reviewed record of science sign in
Pith

arxiv: 2404.00629 · v2 · pith:UGMTXXMR · submitted 2024-03-31 · cs.CL

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:UGMTXXMRrecord.jsonopen to challenge →

classification cs.CL
keywords surveymodelsteaminggenerativevariousachillesadditionallyaddressing
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Adaptive Instruction Composition for Automated LLM Red-Teaming

    cs.CR 2026-04 unverdicted novelty 7.0

    Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.

  2. Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models

    cs.CR 2026-06 unverdicted novelty 6.0

    A narrative survey that catalogs fifty papers on diffusion-based adversarial techniques across text, vision, and vision-language models, proposes a six-class taxonomy of diffusion roles plus a unified five-dimension e...