{"total":32,"rows":[{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"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":"2106.15093","title":"Certifiable Machine Unlearning for Linear Models","created":"2021-06-29","cited_by_count":42,"area":"safety"},{"id":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"id":"2210.09671","title":"Not All Poisons are Created Equal: Robust Training against Data Poisoning","created":"2022-10-18","cited_by_count":30,"area":"safety"},{"id":"2408.00929","title":"Verification of Machine Unlearning is Fragile","created":"2024-08-01","cited_by_count":21,"area":"safety"},{"id":"2302.08990","title":"Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection","created":"2023-02-17","cited_by_count":20,"area":"safety"},{"id":"2411.15537","title":"MUNBa: Machine Unlearning via Nash Bargaining","created":"2024-11-23","cited_by_count":17,"area":"safety"},{"id":"2403.13027","title":"Towards Better Statistical Understanding of Watermarking LLMs","created":"2024-03-19","cited_by_count":16,"area":"safety"},{"id":"2406.07687","title":"Adversarial Machine Unlearning","created":"2024-06-11","cited_by_count":16,"area":"safety"},{"id":"2601.07072","title":"Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems","created":"2026-01-11","cited_by_count":16,"area":"safety"},{"id":"2506.05314","title":"Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2402.05453","title":"Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss","created":"2024-02-08","cited_by_count":6,"area":"safety"},{"id":"2505.07640","title":"Certified Data Removal Under High-dimensional Settings","created":"2025-05-12","cited_by_count":6,"area":"safety"},{"id":"2510.13094","title":"Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach","created":"2025-10-15","cited_by_count":6,"area":"safety"},{"id":"2408.01689","title":"Controllable Unlearning for Image-to-Image Generative Models via $\\varepsilon$-Constrained Optimization","created":"2024-08-03","cited_by_count":5,"area":"safety"},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4,"area":"safety"},{"id":"2410.04234","title":"Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2410.04682","title":"On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning","created":"2024-10-07","cited_by_count":4,"area":"safety"},{"id":"2504.06446","title":"Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models","created":"2025-04-08","cited_by_count":4,"area":"safety"},{"id":"2411.11039","title":"FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Method","created":"2024-11-17","cited_by_count":3,"area":"safety"},{"id":"2502.16737","title":"Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning","created":"2025-02-23","cited_by_count":3,"area":"safety"},{"id":"2502.17081","title":"Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning","created":"2025-02-24","cited_by_count":3,"area":"safety"},{"id":"2409.08985","title":"Clean Label Attacks against SLU Systems","created":"2024-09-13","cited_by_count":2,"area":"safety"},{"id":"2604.23046","title":"Shape of Memory: a Geometric Analysis of Machine Unlearning in Second-Order Optimizers","created":"2026-04-24","cited_by_count":1,"area":"safety"},{"id":"2602.20102","title":"BarrierSteer: LLM Safety via Learning Barrier Steering","created":"2026-02-23","cited_by_count":0,"area":"safety"},{"id":"2604.00422","title":"Shapley-Guided Neural Repair Approach via Derivative-Free Optimization","created":"2026-04-01","cited_by_count":0,"area":"safety"},{"id":"2605.17128","title":"New Wide-Net-Casting Jailbreak Attacks Risk Large Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.17590","title":"Form and Function: Machine Unlearning as a Problem of Misaligned States","created":"2026-05-17","cited_by_count":0,"area":"safety"},{"id":"2608.28646","title":"BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice","created":"2026-08-14","cited_by_count":0,"area":"safety"},{"id":"2609.24377","title":"On the Information-Theoretic Limits of Latent-Space Watermarking Through Pretrained Generators","created":"2026-09-21","cited_by_count":0,"area":"safety"},{"id":"2609.33774","title":"Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech","created":"2026-09-27","cited_by_count":0,"area":"safety"}],"next_cursor":null}