SOTAVerified

Red Teaming

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 251 papers

TitleStatusHype
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic PromptsCode1
RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity SearchCode1
Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationCode1
Causality Analysis for Evaluating the Security of Large Language ModelsCode1
PrivAgent: Agentic-based Red-teaming for LLM Privacy LeakageCode1
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' JailbreakCode1
Probabilistic Inference in Language Models via Twisted Sequential Monte CarloCode1
Control Risk for Potential Misuse of Artificial Intelligence in ScienceCode1
RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn JailbreakingCode1
Defending Against Unforeseen Failure Modes with Latent Adversarial TrainingCode1
Learning diverse attacks on large language models for robust red-teaming and safety tuningCode1
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language ModelsCode1
Jailbroken: How Does LLM Safety Training Fail?Code1
Jailbreaking as a Reward Misspecification ProblemCode1
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and BiasesCode1
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingCode1
AI Control: Improving Safety Despite Intentional SubversionCode1
Large Language Model UnlearningCode1
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS EnvironmentsCode1
Attack Prompt Generation for Red Teaming and Defending Large Language ModelsCode1
Gandalf the Red: Adaptive Security for LLMsCode1
A Safe Harbor for AI Evaluation and Red Teaming—0
CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring—0
Adversaries Can Misuse Combinations of Safe Models—0
Conversational Complexity for Assessing Risk in Large Language Models—0
Investigating Bias Representations in Llama 2 Chat via Activation Steering—0
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming—0
Computational Red Teaming in a Sudoku Solving Context: Neural Network Based Skill Representation and Acquisition—0
CELL your Model: Contrastive Explanations for Large Language Models—0
Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts—0
IterAlign: Iterative Constitutional Alignment of Large Language Models—0
A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming—0
Can Large Language Models Change User Preference Adversarially?—0
A Red Teaming Roadmap Towards System-Level Safety—0
GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models—0
Can Large Language Models Automatically Jailbreak GPT-4V?—0
Can Language Models be Instructed to Protect Personal Information?—0
A Red Teaming Framework for Securing AI in Maritime Autonomous Systems—0
Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models—0
Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems—0
A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management—0
Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis—0
JAB: Joint Adversarial Prompting and Belief Augmentation—0
Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols—0
LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs—0
FLIRT: Feedback Loop In-context Red Teaming—0
GhostPrompt: Jailbreaking Text-to-image Generative Models based on Dynamic Optimization—0
A Multi-Disciplinary Review of Knowledge Acquisition Methods: From Human to Autonomous Eliciting Agents—0
Finding Safety Neurons in Large Language Models—0
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI—0
Show:102550
← PrevPage 2 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SUDOAttack Success Rate41—Unverified