SOTAVerified

Red Teaming

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 226–250 of 251 papers

TitleStatusHype
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts—0
Stealthy and Persistent Unalignment on Large Language Models via Backdoor InjectionsCode0
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications—0
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming—0
Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming—0
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B—0
Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models—0
ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language ModelsCode0
Low-Resource Languages Jailbreak GPT-4—0
Can Language Models be Instructed to Protect Personal Information?—0
No Offense Taken: Eliciting Offensiveness from Language ModelsCode0
Red Teaming Generative AI/NLP, the BB84 quantum cryptography protocol and the NIST-approved Quantum-Resistant Cryptographic Algorithms—0
The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward—0
FLIRT: Feedback Loop In-context Red Teaming—0
Model Card and Evaluations for Claude Models—0
Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses—0
Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback—0
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity—0
Can Large Language Models Change User Preference Adversarially?—0
Red-Teaming the Stable Diffusion Safety Filter—0
Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL AgentsCode0
CTI4AI: Threat Intelligence Generation and Sharing after Red Teaming AI Models—0
Automating Privilege Escalation with Deep Reinforcement Learning—0
A Multi-Disciplinary Review of Knowledge Acquisition Methods: From Human to Autonomous Eliciting Agents—0
Computational Red Teaming in a Sudoku Solving Context: Neural Network Based Skill Representation and Acquisition—0
Show:102550
← PrevPage 10 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SUDOAttack Success Rate41—Unverified