SOTAVerified

Red Teaming

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 251 papers

TitleStatusHype
CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge—0
CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models—0
DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions—0
Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs—0
Atoxia: Red-teaming Large Language Models with Target Toxic Answers—0
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization—0
Digital cloning of online social networks for language-sensitive agent-based modeling of misinformation spread—0
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models—0
Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning—0
DMRL: Data- and Model-aware Reward Learning for Data Extraction—0
Show:102550
← PrevPage 15 of 26Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SUDOAttack Success Rate41—Unverified