Image de couverture de livre

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mazeika, Mantas, Phan, Long, Yin, Xuwang, Zou, Andy, Wang, Zifan, Mu, Norman, Sakhaee, Elham, Li, Nathaniel, Basart, Steven, Li, Bo, Forsyth, David, Hendrycks, Dan
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TextQuests: How Good are LLMs at Text-Based Video Games?
par: Phan, Long, et autres
Publié: (2025)

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
par: Mazeika, Mantas, et autres
Publié: (2025)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
par: Ren, Richard, et autres
Publié: (2024)

Representation Engineering: A Top-Down Approach to AI Transparency
par: Zou, Andy, et autres
Publié: (2023)

GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
par: Cobben, Pepijn, et autres
Publié: (2026)

Tamper-Resistant Safeguards for Open-Weight LLMs
par: Tamirisa, Rishub, et autres
Publié: (2024)

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services
par: Dimino, Fabrizio, et autres
Publié: (2026)

Aggressive Compression Enables LLM Weight Theft
par: Brown, Davis, et autres
Publié: (2026)

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
par: Ren, Richard, et autres
Publié: (2025)

LLMs Encode Harmfulness and Refusal Separately
par: Zhao, Jiachen, et autres
Publié: (2025)

Adaptive Instruction Composition for Automated LLM Red-Teaming
par: Zymet, Jesse, et autres
Publié: (2026)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
par: Andriushchenko, Maksym, et autres
Publié: (2024)

Automated Progressive Red Teaming
par: Jiang, Bojian, et autres
Publié: (2024)

Should LLM Safety Be More Than Refusing Harmful Instructions?
par: Maskey, Utsav, et autres
Publié: (2025)

Anecdoctoring: Automated Red-Teaming Across Language and Place
par: Cuevas, Alejandro, et autres
Publié: (2025)

Can LLMs Follow Simple Rules?
par: Mu, Norman, et autres
Publié: (2023)

Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models
par: Van Doren, Madison, et autres
Publié: (2025)

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models
par: Dang, Quy-Anh, et autres
Publié: (2026)

Effective Automation to Support the Human Infrastructure in AI Red Teaming
par: Zhang, Alice Qian, et autres
Publié: (2025)

Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
par: Han, Vernon Toh Yan, et autres
Publié: (2024)

"Even GPT Can Reject Me": Conceptualizing Abrupt Refusal Secondary Harm (ARSH) and Reimagining Psychological AI Safety with Compassionate Completion Standard (CCS)
par: Ni, Yang, et autres
Publié: (2025)

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
par: Muhamed, Aashiq, et autres
Publié: (2025)

Improving Alignment and Robustness with Circuit Breakers
par: Zou, Andy, et autres
Publié: (2024)

Red Teaming Visual Language Models
par: Li, Mukai, et autres
Publié: (2024)

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
par: Quaye, Jessica, et autres
Publié: (2024)

Multi-lingual Multi-turn Automated Red Teaming for LLMs
par: Singhania, Abhishek, et autres
Publié: (2025)

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
par: An, Bang, et autres
Publié: (2024)

Prompt Optimization and Evaluation for LLM Automated Red Teaming
par: Freenor, Michael, et autres
Publié: (2025)

STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
par: Jung, MinJae, et autres
Publié: (2026)

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
par: Wei, Zhang, et autres
Publié: (2025)

Introduction to AI Safety, Ethics, and Society
par: Hendrycks, Dan
Publié: (2024)

OR-Bench: An Over-Refusal Benchmark for Large Language Models
par: Cui, Justin, et autres
Publié: (2024)

AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
par: Diao, Muxi, et autres
Publié: (2025)

Where Do Reasoning Models Refuse?
par: Yamaguchi, Kureha, et autres
Publié: (2025)

Red Teaming AI Red Teaming
par: Majumdar, Subhabrata, et autres
Publié: (2025)

Training a General Purpose Automated Red Teaming Model
par: Padmakumar, Aishwarya, et autres
Publié: (2026)

Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
par: Götting, Jasper, et autres
Publié: (2025)

DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models
par: Ren, Kaixuan, et autres
Publié: (2025)

FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)
par: Priyanshu, Aman, et autres
Publié: (2024)

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
par: Lin, Lizhi, et autres
Publié: (2024)