{"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":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","cited_by_count":4,"area":"safety"},{"id":"2511.11020","title":"Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis","created":"2025-11-14","cited_by_count":3,"area":"safety"},{"id":"2602.10382","title":"Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"safety"},{"id":"2602.13427","title":"Backdooring Bias in Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"safety"},{"id":"2603.02262","title":"Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs","created":"2026-02-28","cited_by_count":1,"area":"safety"},{"id":"2603.10806","title":"Backdoor Directions in Vision Transformers","created":"2026-03-11","cited_by_count":1,"area":"safety"},{"id":"2605.06846","title":"Narrow Secret Loyalty Dodges Black-Box Audits","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2606.03785","title":"Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs","created":"2026-06-02","cited_by_count":1,"area":"safety"},{"id":"2607.26849","title":"ToxScreen: Detecting Whether an LLM Has Been Poisoned","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2512.02786","title":"FiMMIA: scaling semantic perturbation-based membership inference across modalities","created":"2025-12-02","cited_by_count":0,"area":"safety"},{"id":"2603.17174","title":"Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.12548","title":"DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection","created":"2026-04-14","cited_by_count":0,"area":"safety"},{"id":"2606.16242","title":"Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2607.01729","title":"DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"safety"},{"id":"2607.04146","title":"!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics","created":"2026-07-05","cited_by_count":0,"area":"safety"},{"id":"2607.22657","title":"Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS","created":"2026-06-27","cited_by_count":0,"area":"safety"},{"id":"2609.32288","title":"A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents","created":"2026-09-26","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"}],"next_cursor":null}