SOTAVerified

Red Teaming

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 251 papers

TitleStatusHype
garak: A Framework for Security Probing Large Language ModelsCode9
PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI SystemCode7
Seamless: Multilingual Expressive and Streaming Speech TranslationCode6
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalCode4
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedCode3
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMsCode3
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge BasesCode3
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially FastCode2
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language ModelsCode2
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Code2
Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail ModerationCode2
Against The Achilles' Heel: A Survey on Red Teaming for Generative ModelsCode2
Jailbreak Vision Language Models via Bi-Modal Adversarial PromptCode2
Curiosity-driven Red-teaming for Large Language ModelsCode2
Improved Techniques for Optimization-Based Jailbreaking on Large Language ModelsCode2
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red TeamingCode2
Tamper-Resistant Safeguards for Open-Weight LLMsCode2
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherCode2
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMsCode2
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak PromptsCode2
Reliable and Efficient Concept Erasure of Text-to-Image Diffusion ModelsCode2
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks YetCode2
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring TechniqueCode1
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn PlannerCode1
Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image GenerationCode1
Show:102550
← PrevPage 1 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SUDOAttack Success Rate41—Unverified