{"total":92,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"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":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2410.09760","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","created":"2024-10-13","cited_by_count":37,"area":"alignment"},{"id":"2412.12497","title":"NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning","created":"2024-12-17","cited_by_count":37,"area":"alignment"},{"id":"2410.18210","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","created":"2024-10-23","cited_by_count":33,"area":"safety"},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22,"area":"safety"},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2506.05346","title":"Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets","created":"2025-06-05","cited_by_count":20,"area":"alignment"},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"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":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"id":"2505.12038","title":"Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets","created":"2025-05-17","cited_by_count":18,"area":null},{"id":"2506.03850","title":"Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning","created":"2025-06-04","cited_by_count":17,"area":"alignment"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"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":"2412.19512","title":"Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2508.07172","title":"Gradient Surgery for Safe LLM Fine-Tuning","created":"2025-08-10","cited_by_count":11,"area":"alignment"},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2512.10150","title":"Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning","created":"2025-12-10","cited_by_count":10,"area":"alignment"},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2410.04524","title":"Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2509.15202","title":"Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2509.22745","title":"Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment","created":"2025-09-26","cited_by_count":8,"area":"moe"},{"id":"2601.01887","title":"Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance","created":"2026-01-05","cited_by_count":8,"area":"alignment"},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2505.19670","title":"Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2601.10141","title":"Understanding and Preserving Safety in Fine-Tuned LLMs","created":"2026-01-15","cited_by_count":7,"area":"safety"},{"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":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2505.14185","title":"Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study","created":"2025-05-20","cited_by_count":6,"area":"alignment"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2505.23724","title":"SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"id":"2511.14423","title":"Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education","created":"2025-11-18","cited_by_count":5,"area":"safety"},{"id":"2409.12914","title":"Evaluating Defences against Unsafe Feedback in RLHF","created":"2024-09-19","cited_by_count":4,"area":"alignment"},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2603.07445","title":"Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning","created":"2026-03-08","cited_by_count":4,"area":"alignment"},{"id":"2604.12384","title":"Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2604.17215","title":"Continual Safety Alignment via Gradient-Based Sample Selection","created":"2026-04-19","cited_by_count":4,"area":"alignment"},{"id":"2505.04578","title":"Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization","created":"2025-05-07","cited_by_count":3,"area":"safety"},{"id":"2512.01899","title":"Provably Safe Model Updates","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2,"area":"safety"},{"id":"2508.09190","title":"Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2510.01342","title":"Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach","created":"2025-10-01","cited_by_count":2,"area":"safety"},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2601.07200","title":"Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment","created":"2026-01-12","cited_by_count":2,"area":"alignment"},{"id":"2602.06911","title":"TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering","created":"2026-02-06","cited_by_count":2,"area":"safety"},{"id":"2606.02995","title":"Patcher: Post-Hoc Patching of Backdoored Large Language Models","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2502.01436","title":"Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2506.00676","title":"SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning","created":"2025-05-31","cited_by_count":1,"area":"alignment"},{"id":"2506.23799","title":"KAIROS: Scalable Model-Agnostic Data Valuation","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2603.00061","title":"The Hidden Costs of Domain Fine-Tuning: Pii-Bearing Data Degrades Safety and Increases Leakage","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2604.07655","title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.13043","title":"Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models","created":"2026-05-13","cited_by_count":1,"area":"diffusion"},{"id":"2605.25073","title":"Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions","created":"2026-05-24","cited_by_count":1,"area":"safety"},{"id":"2606.06519","title":"SafeGene: Reusable Adapters for Transferable Safety Alignment","created":"2026-06-02","cited_by_count":1,"area":"alignment"},{"id":"2507.05660","title":"Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI","created":"2025-07-08","cited_by_count":0,"area":"alignment"},{"id":"2602.02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","created":"2026-02-02","cited_by_count":0,"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":"2603.07452","title":"Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs","created":"2026-03-08","cited_by_count":0,"area":"safety"},{"id":"2604.17691","title":"SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models","created":"2026-04-20","cited_by_count":0,"area":"alignment"},{"id":"2605.02914","title":"When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2605.05995","title":"Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks","created":"2026-05-07","cited_by_count":0,"area":"alignment"},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2605.28030","title":"SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.30263","title":"Defending Against Harmful Supervision Hidden in Benign Samples","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2607.11475","title":"HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models","created":"2026-07-13","cited_by_count":0,"area":"alignment"},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.22144","title":"Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","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}],"next_cursor":null}