| Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars | Dec 10, 2024 | Safety Alignment | —Unverified | 0 |
| SafeWorld: Geo-Diverse Safety Alignment | Dec 9, 2024 | Safety Alignment | CodeCode Available | 0 |
| PrivAgent: Agentic-based Red-teaming for LLM Privacy Leakage | Dec 7, 2024 | Red TeamingSafety Alignment | CodeCode Available | 1 |
| Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models | Nov 30, 2024 | Safety Alignment | —Unverified | 0 |
| PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning | Nov 28, 2024 | Federated Learningparameter-efficient fine-tuning | —Unverified | 0 |
| Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment | Nov 27, 2024 | Safety AlignmentVisual Reasoning | CodeCode Available | 1 |
| Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models | Nov 27, 2024 | Image GenerationSafety Alignment | —Unverified | 0 |
| Don't Command, Cultivate: An Exploratory Study of System-2 Alignment | Nov 26, 2024 | Prompt EngineeringSafety Alignment | CodeCode Available | 0 |
| Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine | Nov 20, 2024 | FairnessSafety Alignment | —Unverified | 0 |
| PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment | Nov 18, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
