{"total":54,"rows":[{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"area":"safety"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98,"area":"safety"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86,"area":"safety"},{"id":"2406.15968","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","created":"2024-06-23","cited_by_count":64,"area":"safety"},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","cited_by_count":56,"area":"safety"},{"id":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40,"area":"safety"},{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2403.09562","title":"PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps","created":"2024-03-14","cited_by_count":23,"area":"safety"},{"id":"2407.10058","title":"Learning to Refuse: Towards Mitigating Privacy Risks in LLMs","created":"2024-07-14","cited_by_count":23,"area":"safety"},{"id":"2404.11262","title":"Sampling-based Pseudo-Likelihood for Membership Inference Attacks","created":"2024-04-17","cited_by_count":20,"area":"safety"},{"id":"2403.10557","title":"Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models","created":"2024-03-13","cited_by_count":18,"area":"safety"},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2409.11844","title":"MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts","created":"2024-09-18","cited_by_count":18,"area":"safety"},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2502.19726","title":"Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training","created":"2025-02-27","cited_by_count":15,"area":"safety"},{"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":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2406.14091","title":"Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models","created":"2024-06-20","cited_by_count":10,"area":"safety"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2501.16663","title":"Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning","created":"2025-01-28","cited_by_count":9,"area":"safety"},{"id":"2509.13755","title":"Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning","created":"2025-09-17","cited_by_count":7,"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":"2506.14913","title":"Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning","created":"2025-06-17","cited_by_count":6,"area":"safety"},{"id":"2407.20271","title":"Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models","created":"2024-07-25","cited_by_count":5,"area":"safety"},{"id":"2502.15010","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","created":"2025-02-20","cited_by_count":5,"area":"safety"},{"id":"2601.18110","title":"AttenMIA: LLM Membership Inference Attack through Attention Signals","created":"2026-01-26","cited_by_count":4,"area":"safety"},{"id":"2412.21123","title":"ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation","created":"2024-12-30","cited_by_count":3,"area":"safety"},{"id":"2501.17501","title":"How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning","created":"2025-01-29","cited_by_count":3,"area":"safety"},{"id":"2503.07697","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"safety"},{"id":"2506.20856","title":"Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA","created":"2025-06-25","cited_by_count":3,"area":"safety"},{"id":"2405.08134","title":"Many-Shot Regurgitation (MSR) Prompting","created":"2024-05-13","cited_by_count":2,"area":"safety"},{"id":"2412.08549","title":"Watermarking Training Data of Music Generation Models","created":"2024-12-11","cited_by_count":2,"area":"safety"},{"id":"2510.05753","title":"Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning","created":"2025-10-07","cited_by_count":0,"area":"safety"},{"id":"2512.12914","title":"CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2601.12937","title":"On the Evidentiary Limits of Membership Inference for Copyright Auditing","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2603.01550","title":"Extracting Training Dialogue Data from Large Language Model based Task Bots","created":"2026-03-02","cited_by_count":0,"area":"safety"},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}