| No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks | May 25, 2024 | Safety Alignment | —Unverified | 0 |
| Off-Policy Risk Assessment in Markov Decision Processes | Sep 21, 2022 | Multi-Armed BanditsSafety 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 |
| RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models | Nov 16, 2023 | Backdoor AttackData Poisoning | —Unverified | 0 |
| On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept | Jun 4, 2024 | Question AnsweringSafety Alignment | —Unverified | 0 |
| PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach | Sep 21, 2024 | Multi-agent Reinforcement LearningSafety 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 |
| PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference | Jun 20, 2024 | Question AnsweringSafety Alignment | —Unverified | 0 |
| Playing Language Game with LLMs Leads to Jailbreaking | Nov 16, 2024 | Safety Alignment | —Unverified | 0 |
| PoisonSwarm: Universal Harmful Information Synthesis via Model Crowdsourcing | May 27, 2025 | counterfactualDiversity | —Unverified | 0 |
