| SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks | Oct 2, 2024 | Safety Alignment | —Unverified | 0 |
| Towards Inference-time Category-wise Safety Steering for Large Language Models | Oct 2, 2024 | Safety Alignment | —Unverified | 0 |
| Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models | Oct 1, 2024 | Safety Alignment | CodeCode Available | 0 |
| Overriding Safety protections of Open-source Models | Sep 28, 2024 | Red TeamingSafety Alignment | CodeCode Available | 0 |
| Backtracking Improves Generation Safety | Sep 22, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach | Sep 21, 2024 | Multi-agent Reinforcement LearningSafety Alignment | —Unverified | 0 |
| Mitigating Unsafe Feedback with Learning Constraints | Sep 19, 2024 | Safety AlignmentText Generation | —Unverified | 0 |
| Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer | Aug 21, 2024 | Safety Alignment | CodeCode Available | 0 |
| Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation | Aug 20, 2024 | Safety Alignment | —Unverified | 0 |
| Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions | Aug 14, 2024 | Safety Alignment | CodeCode Available | 0 |
