| Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation | May 24, 2025 | Intent DetectionNatural Language Understanding | —Unverified | 0 |
| MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming | May 22, 2025 | Red TeamingSafety Alignment | CodeCode Available | 1 |
| Towards medical AI misalignment: a preliminary study | May 22, 2025 | Red Teaming | —Unverified | 0 |
| RRTL: Red Teaming Reasoning Large Language Models in Tool Learning | May 21, 2025 | Red Teaming | —Unverified | 0 |
| EVA: Red-Teaming GUI Agents via Evolving Indirect Prompt Injection | May 20, 2025 | Red Teaming | —Unverified | 0 |
| Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities | May 20, 2025 | Red Teaming | CodeCode Available | 0 |
| "Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs | May 20, 2025 | Image GenerationRed Teaming | —Unverified | 0 |
| Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents | May 20, 2025 | Contrastive LearningRed Teaming | —Unverified | 0 |
| CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models | May 19, 2025 | BenchmarkingRed Teaming | —Unverified | 0 |
| LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs | May 16, 2025 | Red Teaming | —Unverified | 0 |
