{"total":27,"rows":[{"id":"2402.09063","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","created":"2024-02-14","cited_by_count":91,"area":"alignment"},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2506.16447","title":"Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2402.01920","title":"Preference Poisoning Attacks on Reward Model Learning","created":"2024-02-02","cited_by_count":14,"area":"alignment"},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2409.00787","title":"The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs","created":"2024-09-01","cited_by_count":10,"area":"alignment"},{"id":"2602.06258","title":"GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt","created":"2026-02-05","cited_by_count":7,"area":"alignment"},{"id":"2404.16020","title":"Investigating Adversarial Trigger Transfer in Large Language Models","created":"2024-04-24","cited_by_count":5,"area":"alignment"},{"id":"2410.11283","title":"AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment","created":"2024-10-15","cited_by_count":5,"area":"alignment"},{"id":"2503.03039","title":"LLM Misalignment via Adversarial RLHF Platforms","created":"2025-03-04","cited_by_count":5,"area":"alignment"},{"id":"2412.08201","title":"Model-Editing-Based Jailbreak against Safety-aligned Large Language Models","created":"2024-12-11","cited_by_count":4,"area":"alignment"},{"id":"2503.10228","title":"Policy Teaching via Data Poisoning in Learning from Human Preferences","created":"2025-03-13","cited_by_count":2,"area":"alignment"},{"id":"2503.12301","title":"One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2506.03234","title":"BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2507.02850","title":"LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2507.08020","title":"Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation","created":"2025-07-08","cited_by_count":2,"area":"alignment"},{"id":"2606.02995","title":"Patcher: Post-Hoc Patching of Backdoored Large Language Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2506.13285","title":"DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulation","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2510.09260","title":"GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis","created":"2025-10-10","cited_by_count":1,"area":"alignment"},{"id":"2605.02495","title":"Efficient Preference Poisoning Attack on Offline RLHF","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2605.16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2603.28281","title":"Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2605.05995","title":"Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks","created":"2026-05-07","cited_by_count":0,"area":"alignment"},{"id":"2605.07883","title":"Beyond \"I cannot fulfill this request\": Alleviating Rigid Rejection in LLMs via Label Enhancement","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.04929","title":"Sequential Data Poisoning in LLM Post-Training","created":"2026-06-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}