{"total":32,"rows":[{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118,"area":"safety"},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","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":"2205.13680","title":"Membership Inference Attack Using Self Influence Functions","created":"2022-05-26","cited_by_count":20,"area":"safety"},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2111.03120","title":"Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods","created":"2021-11-04","cited_by_count":16,"area":"safety"},{"id":"2402.15109","title":"Remaining-data-free Machine Unlearning by Suppressing Sample Contribution","created":"2024-02-23","cited_by_count":13,"area":"safety"},{"id":"2504.10185","title":"LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks","created":"2025-04-14","cited_by_count":12,"area":"safety"},{"id":"2502.05911","title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","created":"2025-02-09","cited_by_count":11,"area":"safety"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2411.05743","title":"Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods","created":"2024-11-08","cited_by_count":7,"area":"safety"},{"id":"2412.02432","title":"Improved Localized Machine Unlearning Through the Lens of Memorization","created":"2024-12-03","cited_by_count":6,"area":"safety"},{"id":"2209.15276","title":"Machine Unlearning Method Based On Projection Residual","created":"2022-09-30","cited_by_count":4,"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":"2604.07962","title":"Is your algorithm unlearning or untraining?","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2604.16591","title":"Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning","created":"2026-04-17","cited_by_count":2,"area":"safety"},{"id":"2505.16147","title":"Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value","created":"2025-05-22","cited_by_count":1,"area":"safety"},{"id":"2508.01620","title":"IMU: Influence-guided Machine Unlearning","created":"2025-08-03","cited_by_count":1,"area":"safety"},{"id":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2509.16525","title":"CAF\\'E: Causal Black-Box Testing of Machine Unlearning","created":"2025-09-20","cited_by_count":0,"area":"safety"},{"id":"2512.04457","title":"RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2512.05254","title":"When unlearning is free: leveraging low influence points to reduce computational costs","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2604.16536","title":"Towards Reliable Testing of Machine Unlearning","created":"2026-04-16","cited_by_count":0,"area":"safety"},{"id":"2605.05687","title":"DataDignity: Training Data Attribution for Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.17610","title":"SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening","created":"2026-05-17","cited_by_count":0,"area":"safety"},{"id":"2606.17123","title":"LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2607.28829","title":"When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks","created":"2026-07-30","cited_by_count":0,"area":"safety"},{"id":"2608.26743","title":"Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.15044","title":"Data Attribution via Sketched Metadifferentiation","created":"2026-09-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}