{"total":25,"rows":[{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","cited_by_count":6,"area":"safety"},{"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":"2510.17021","title":"Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning","created":"2025-10-19","cited_by_count":6,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2602.13427","title":"Backdooring Bias in Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"safety"},{"id":"2604.21700","title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","created":"2026-04-23","cited_by_count":1,"area":"safety"},{"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":"2508.02312","title":"Data Security in Large Language Models: Risks, Defense, and Directions","created":"2025-08-04","cited_by_count":0,"area":"safety"},{"id":"2603.07452","title":"Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs","created":"2026-03-08","cited_by_count":0,"area":"safety"},{"id":"2603.20108","title":"Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition","created":"2026-03-20","cited_by_count":0,"area":"safety"},{"id":"2604.27426","title":"Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors","created":"2026-04-30","cited_by_count":0,"area":"safety"},{"id":"2605.19147","title":"Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2605.26595","title":"Cordyceps: Covert Control Attacks on LLMs via Data Poisoning","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2606.00654","title":"The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction","created":"2026-05-30","cited_by_count":0,"area":"safety"},{"id":"2606.30899","title":"Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2608.24354","title":"Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs","created":"2026-08-25","cited_by_count":0,"area":"safety"},{"id":"2609.06612","title":"MechAudit-40: White-Box Auditing across 40 LLM Attack Mechanisms","created":"2026-09-06","cited_by_count":0,"area":"safety"},{"id":"2610.00348","title":"Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.00663","title":"Backdoor Containment via Expert Quarantine and Shutdown in LLMs","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.00685","title":"Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.06049","title":"Backdooring Sparse Autoencoders","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.12644","title":"Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller","created":"2026-10-08","cited_by_count":0,"area":"safety"},{"id":"2610.14701","title":"Towards Merging-conditional Backdoor Unalignment against Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}