| SafeVid: Toward Safety Aligned Video Large Multimodal Models | May 17, 2025 | Safety Alignment | —Unverified | 0 |
| Noise Injection Systemically Degrades Large Language Model Safety Guardrails | May 16, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction | May 16, 2025 | Contrastive LearningSafety Alignment | CodeCode Available | 2 |
| CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs | May 16, 2025 | Adversarial RobustnessSafety Alignment | —Unverified | 0 |
| Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data | May 15, 2025 | Malware DetectionSafety Alignment | —Unverified | 0 |
| One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models | May 12, 2025 | Code GenerationSafety Alignment | —Unverified | 0 |
| FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning | May 12, 2025 | 16kBenchmarking | —Unverified | 0 |
| Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety | May 11, 2025 | Outlier DetectionRed Teaming | CodeCode Available | 0 |
| Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model | May 10, 2025 | Safety Alignment | CodeCode Available | 0 |
| NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models | Apr 29, 2025 | Safety Alignment | —Unverified | 0 |
