SOTAVerified

Red Teaming

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 251 papers

TitleStatusHype
Aloe: A Family of Fine-tuned Open Healthcare LLMsCode1
Probabilistic Inference in Language Models via Twisted Sequential Monte CarloCode1
Defending Against Unforeseen Failure Modes with Latent Adversarial TrainingCode1
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image GenerationCode1
Causality Analysis for Evaluating the Security of Large Language ModelsCode1
AI Control: Improving Safety Despite Intentional SubversionCode1
Control Risk for Potential Misuse of Artificial Intelligence in ScienceCode1
Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-AlignmentCode1
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and BiasesCode1
Attack Prompt Generation for Red Teaming and Defending Large Language ModelsCode1
Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?Code1
Large Language Model UnlearningCode1
Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationCode1
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic PromptsCode1
Red-Teaming Large Language Models using Chain of Utterances for Safety-AlignmentCode1
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language ModelsCode1
Jailbroken: How Does LLM Safety Training Fail?Code1
Explore, Establish, Exploit: Red Teaming Language Models from ScratchCode1
Red Teaming Language Model Detectors with Language ModelsCode1
Query-Efficient Black-Box Red Teaming via Bayesian OptimizationCode1
Red Teaming Language Models with Language ModelsCode1
RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource LanguagesCode0
STACK: Adversarial Attacks on LLM Safeguard Pipelines—0
We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent SystemsCode0
Effective Red-Teaming of Policy-Adherent Agents—0
Show:102550
← PrevPage 3 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SUDOAttack Success Rate41—Unverified