| Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs) | Jul 20, 2024 | Red Teaming | CodeCode Available | 1 |
| Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle | Jul 18, 2024 | BenchmarkingLanguage Modeling | —Unverified | 0 |
| Direct Unlearning Optimization for Robust and Safe Text-to-Image Models | Jul 17, 2024 | Red Teaming | —Unverified | 0 |
| AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases | Jul 17, 2024 | Autonomous DrivingBackdoor Attack | CodeCode Available | 3 |
| Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models | Jul 17, 2024 | BenchmarkingRed Teaming | CodeCode Available | 2 |
| ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts | Jul 12, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| The Human Factor in AI Red Teaming: Perspectives from Social and Collaborative Computing | Jul 10, 2024 | FairnessRed Teaming | —Unverified | 0 |
| Automated Progressive Red Teaming | Jul 4, 2024 | Active LearningRed Teaming | CodeCode Available | 0 |
| SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters | Jul 2, 2024 | Red TeamingSafety Alignment | CodeCode Available | 0 |
| Purple-teaming LLMs with Adversarial Defender Training | Jul 1, 2024 | Generative Adversarial NetworkRed Teaming | —Unverified | 0 |
