{"total":20,"rows":[{"id":"2602.03085","title":"The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers","created":"2026-02-03","cited_by_count":14,"area":"safety"},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2507.11630","title":"Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility","created":"2025-07-15","cited_by_count":9,"area":"safety"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","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":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2601.06641","title":"Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning","created":"2026-01-10","cited_by_count":1,"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":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","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":"2512.03089","title":"Password-Activated Shutdown Protocols for Misaligned Frontier Agents","created":"2025-11-29","cited_by_count":0,"area":"safety"},{"id":"2604.17384","title":"Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion","created":"2026-04-19","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":"2605.11612","title":"When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2606.29646","title":"Fuzzing Large Language Models to Elicit Hidden Behaviours","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2606.31309","title":"CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2608.06779","title":"Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models","created":"2026-08-07","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"}],"next_cursor":null}