| Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI | Mar 12, 2024 | Hyperspectral image analysisHYPERVIEW Challenge | —Unverified | 0 |
| Defending Against Unforeseen Failure Modes with Latent Adversarial Training | Mar 8, 2024 | image-classificationImage Classification | CodeCode Available | 1 |
| Aligners: Decoupling LLMs and Alignment | Mar 7, 2024 | Instruction FollowingRed Teaming | CodeCode Available | 0 |
| A Safe Harbor for AI Evaluation and Red Teaming | Mar 7, 2024 | Red Teaming | —Unverified | 0 |
| Curiosity-driven Red-teaming for Large Language Models | Feb 29, 2024 | Red TeamingReinforcement Learning (RL) | CodeCode Available | 2 |
| AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning | Feb 21, 2024 | Graph Neural NetworkRed Teaming | —Unverified | 0 |
| Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation | Feb 14, 2024 | Image GenerationRed Teaming | CodeCode Available | 1 |
| Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast | Feb 13, 2024 | Language ModellingLarge Language Model | CodeCode Available | 2 |
| HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal | Feb 6, 2024 | Red Teaming | CodeCode Available | 4 |
| Investigating Bias Representations in Llama 2 Chat via Activation Steering | Feb 1, 2024 | Decision MakingRed Teaming | —Unverified | 0 |
