{"total":32,"rows":[{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"id":"2602.04863","title":"Subliminal Effects in Your Data: A General Mechanism via Log-Linearity","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2508.17158","title":"Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks","created":"2025-08-23","cited_by_count":11,"area":null},{"id":"2604.16812","title":"Introspection Adapters: Training LLMs to Report Their Learned Behaviors","created":"2026-04-18","cited_by_count":11,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.16672","title":"The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2503.17388","title":"AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2601.22710","title":"AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2508.20333","title":"Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.02411","title":"A Survey: Towards Privacy and Security in Mobile Large Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2606.17110","title":"Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2602.17546","title":"Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.09411","title":"Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.06851","title":"You Are What You Read: Misalignment via In-Context Persona Induction","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.29960","title":"Beyond Average Safety: Chance-Constrained LLM Fine-tuning","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.03033","title":"When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07518","title":"Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}