{"total":133,"rows":[{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878,"area":"safety"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429,"area":"safety"},{"id":"2306.17439","title":"Provable Robust Watermarking for AI-Generated Text","created":"2023-06-30","cited_by_count":299,"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":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2310.06356","title":"A Semantic Invariant Robust Watermark for Large Language Models","created":"2023-10-10","cited_by_count":112,"area":"safety"},{"id":"2103.15543","title":"Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models","created":"2021-03-29","cited_by_count":105,"area":"safety"},{"id":"2110.07831","title":"RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models","created":"2021-10-15","cited_by_count":104,"area":"safety"},{"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":"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":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"area":"safety"},{"id":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82,"area":"safety"},{"id":"2502.05374","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","created":"2025-02-07","cited_by_count":79,"area":"safety"},{"id":"2310.12362","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","created":"2023-10-18","cited_by_count":78,"area":"safety"},{"id":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"area":"safety"},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67,"area":"safety"},{"id":"2410.19278","title":"Applying sparse autoencoders to unlearn knowledge in language models","created":"2024-10-25","cited_by_count":59,"area":"safety"},{"id":"2308.00221","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","created":"2023-08-01","cited_by_count":57,"area":"safety"},{"id":"2305.19713","title":"Red Teaming Language Model Detectors with Language Models","created":"2023-05-31","cited_by_count":55,"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":"2401.16820","title":"Provably Robust Multi-bit Watermarking for AI-generated Text","created":"2024-01-30","cited_by_count":47,"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":"2405.04825","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","created":"2024-05-08","cited_by_count":40,"area":"safety"},{"id":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","cited_by_count":34,"area":"safety"},{"id":"2406.14517","title":"PostMark: A Robust Blackbox Watermark for Large Language Models","created":"2024-06-20","cited_by_count":29,"area":"safety"},{"id":"2401.10862","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","created":"2024-01-19","cited_by_count":26,"area":"safety"},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2406.01946","title":"Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature","created":"2024-06-04","cited_by_count":25,"area":"safety"},{"id":"2504.08192","title":"SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs","created":"2025-04-11","cited_by_count":22,"area":"safety"},{"id":"2406.16565","title":"Noisy Neighbors: Efficient membership inference attacks against LLMs","created":"2024-06-24","cited_by_count":21,"area":"safety"},{"id":"2506.01339","title":"Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning","created":"2025-06-02","cited_by_count":21,"area":"safety"},{"id":"2503.04636","title":"Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking","created":"2025-03-06","cited_by_count":19,"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":"2505.24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","created":"2025-05-30","cited_by_count":18,"area":"safety"},{"id":"2402.09477","title":"PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining","created":"2024-02-12","cited_by_count":17,"area":"safety"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"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":"2407.04411","title":"Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs","created":"2024-07-05","cited_by_count":15,"area":"safety"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2402.17938","title":"EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models","created":"2024-02-27","cited_by_count":11,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2505.04416","title":"OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models","created":"2025-05-07","cited_by_count":10,"area":"safety"},{"id":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9,"area":"safety"},{"id":"2407.12281","title":"Turning Generative Models Degenerate: The Power of Data Poisoning Attacks","created":"2024-07-17","cited_by_count":9,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2507.06274","title":"Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks","created":"2025-07-08","cited_by_count":9,"area":"safety"},{"id":"2305.09574","title":"UOR: Universal Backdoor Attacks on Pre-trained Language Models","created":"2023-05-16","cited_by_count":8,"area":"safety"},{"id":"2404.04254","title":"Watermark-based Attribution of AI-Generated Content","created":"2024-04-05","cited_by_count":8,"area":"safety"},{"id":"2503.15128","title":"Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors","created":"2025-03-19","cited_by_count":8,"area":"safety"},{"id":"2406.13551","title":"Mitigating Social Biases in Language Models through Unlearning","created":"2024-06-19","cited_by_count":7,"area":"safety"},{"id":"2411.07122","title":"SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs","created":"2024-11-11","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2603.01285","title":"Attention Smoothing Is All You Need For Unlearning","created":"2026-03-01","cited_by_count":7,"area":"safety"},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2408.17354","title":"Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage","created":"2024-08-30","cited_by_count":6,"area":"safety"},{"id":"2503.11127","title":"Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning","created":"2025-03-14","cited_by_count":6,"area":"safety"},{"id":"2405.16783","title":"TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models","created":"2024-05-27","cited_by_count":5,"area":"safety"},{"id":"2409.14513","title":"Order of Magnitude Speedups for LLM Membership Inference","created":"2024-09-22","cited_by_count":5,"area":"safety"},{"id":"2508.06595","title":"LLM Unlearning Without an Expert Curated Dataset","created":"2025-08-08","cited_by_count":5,"area":"safety"},{"id":"2512.19025","title":"The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation","created":"2025-12-22","cited_by_count":5,"area":"safety"},{"id":"2402.14977","title":"Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models","created":"2024-02-22","cited_by_count":4,"area":"safety"},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2407.16951","title":"Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation","created":"2024-07-24","cited_by_count":4,"area":"safety"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2505.02344","title":"An End-to-End Model for Logits-Based Large Language Models Watermarking","created":"2025-05-05","cited_by_count":4,"area":"safety"},{"id":"2506.12484","title":"Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization","created":"2025-06-14","cited_by_count":4,"area":"safety"},{"id":"2511.00030","title":"Probing Knowledge Holes in Unlearned LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2512.06899","title":"Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models","created":"2025-12-07","cited_by_count":4,"area":"safety"},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","cited_by_count":4,"area":"safety"},{"id":"2607.03688","title":"PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks","created":"2026-07-04","cited_by_count":4,"area":"safety"},{"id":"2406.11106","title":"From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models","created":"2024-06-17","cited_by_count":3,"area":"safety"},{"id":"2509.11816","title":"Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning","created":"2025-09-15","cited_by_count":3,"area":"safety"},{"id":"2510.00799","title":"Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors","created":"2025-10-01","cited_by_count":3,"area":"safety"},{"id":"2510.01637","title":"Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking","created":"2025-10-02","cited_by_count":3,"area":"safety"},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","cited_by_count":3,"area":"safety"},{"id":"2510.22376","title":"Label Smoothing Improves Gradient Ascent in LLM Unlearning","created":"2025-10-25","cited_by_count":3,"area":"safety"},{"id":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2406.04478","title":"PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning","created":"2024-06-06","cited_by_count":2,"area":"safety"},{"id":"2502.18518","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2508.06467","title":"LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2510.07626","title":"LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics","created":"2025-10-08","cited_by_count":2,"area":"safety"},{"id":"2510.09007","title":"LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data","created":"2025-10-10","cited_by_count":2,"area":"safety"},{"id":"2510.12316","title":"Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation","created":"2025-10-14","cited_by_count":2,"area":"safety"},{"id":"2602.19275","title":"KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models","created":"2026-02-22","cited_by_count":2,"area":"safety"},{"id":"2606.18473","title":"PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning","created":"2026-06-16","cited_by_count":2,"area":"safety"},{"id":"2402.03303","title":"Nevermind: Instruction Override and Moderation in Large Language Models","created":"2024-02-05","cited_by_count":1,"area":"safety"},{"id":"2403.05842","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","created":"2024-03-09","cited_by_count":1,"area":"safety"},{"id":"2410.18824","title":"PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models","created":"2024-10-24","cited_by_count":1,"area":"safety"},{"id":"2412.12563","title":"Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers","created":"2024-12-17","cited_by_count":1,"area":"safety"},{"id":"2504.06658","title":"A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty","created":"2025-04-09","cited_by_count":1,"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":"2508.12220","title":"Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models","created":"2025-08-17","cited_by_count":1,"area":"safety"}],"next_cursor":"100"}