{"total":629,"rows":[{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878,"area":"safety"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"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":"2103.03279","title":"Remember What You Want to Forget: Algorithms for Machine Unlearning","created":"2021-03-04","cited_by_count":371,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312,"area":"safety"},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302,"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":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279,"area":"safety"},{"id":"2302.09880","title":"Towards Unbounded Machine Unlearning","created":"2023-02-20","cited_by_count":268,"area":"safety"},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"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":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248,"area":"safety"},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"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":"2308.07707","title":"Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening","created":"2023-08-15","cited_by_count":181,"area":"safety"},{"id":"2106.04378","title":"Adaptive Machine Unlearning","created":"2021-06-08","cited_by_count":176,"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":"2110.11891","title":"On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning","created":"2021-10-22","cited_by_count":171,"area":"safety"},{"id":"2111.08440","title":"On the Importance of Difficulty Calibration in Membership Inference Attacks","created":"2021-11-15","cited_by_count":147,"area":"safety"},{"id":"2103.14991","title":"Graph Unlearning","created":"2021-03-27","cited_by_count":138,"area":"safety"},{"id":"2303.11570","title":"Boundary Unlearning","created":"2023-03-21","cited_by_count":134,"area":"safety"},{"id":"2201.05629","title":"Zero-Shot Machine Unlearning","created":"2022-01-14","cited_by_count":133,"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":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2110.11794","title":"Federated Unlearning via Class-Discriminative Pruning","created":"2021-10-22","cited_by_count":115,"area":"safety"},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110,"area":"safety"},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107,"area":"safety"},{"id":"2208.14933","title":"Membership Inference Attacks by Exploiting Loss Trajectory","created":"2022-08-31","cited_by_count":101,"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":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"id":"2102.02551","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","created":"2021-02-04","cited_by_count":85,"area":"safety"},{"id":"2201.06640","title":"Towards Adversarial Evaluations for Inexact Machine Unlearning","created":"2022-01-17","cited_by_count":84,"area":"safety"},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2101.01341","title":"Practical Blind Membership Inference Attack via Differential Comparisons","created":"2021-01-05","cited_by_count":78,"area":"safety"},{"id":"2108.11023","title":"EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning","created":"2021-08-25","cited_by_count":73,"area":"safety"},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"id":"2210.00968","title":"Membership Inference Attacks Against Text-to-image Generation Models","created":"2022-10-03","cited_by_count":69,"area":"safety"},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69,"area":"safety"},{"id":"2110.08324","title":"Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture","created":"2021-10-15","cited_by_count":67,"area":"safety"},{"id":"2301.11578","title":"Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers","created":"2023-01-27","cited_by_count":67,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2302.12580","title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","created":"2023-02-24","cited_by_count":66,"area":"safety"},{"id":"2307.03694","title":"Scalable Membership Inference Attacks via Quantile Regression","created":"2023-07-07","cited_by_count":65,"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":"2310.20448","title":"A Survey on Federated Unlearning: Challenges, Methods, and Future Directions","created":"2023-10-31","cited_by_count":63,"area":"safety"},{"id":"2210.08911","title":"Forget Unlearning: Towards True Data-Deletion in Machine Learning","created":"2022-10-17","cited_by_count":61,"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":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2109.08045","title":"Membership Inference Attacks Against Recommender Systems","created":"2021-09-16","cited_by_count":57,"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":"2104.08305","title":"Membership Inference Attack Susceptibility of Clinical Language Models","created":"2021-04-16","cited_by_count":52,"area":"safety"},{"id":"2106.06916","title":"Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization","created":"2021-06-13","cited_by_count":52,"area":"safety"},{"id":"2109.08266","title":"Hard to Forget: Poisoning Attacks on Certified Machine Unlearning","created":"2021-09-17","cited_by_count":52,"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":"2406.09073","title":"Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition","created":"2024-06-13","cited_by_count":50,"area":"safety"},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50,"area":"safety"},{"id":"2404.03233","title":"Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning","created":"2024-04-04","cited_by_count":48,"area":"safety"},{"id":"2110.12925","title":"CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning","created":"2021-10-25","cited_by_count":47,"area":"safety"},{"id":"2205.12709","title":"VeriFi: Towards Verifiable Federated Unlearning","created":"2022-05-25","cited_by_count":46,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"id":"2406.12038","title":"Soft Prompting for Unlearning in Large Language Models","created":"2024-06-17","cited_by_count":46,"area":"safety"},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","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":"2202.03335","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","created":"2022-02-07","cited_by_count":45,"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":"2209.15266","title":"Data Poisoning Attacks Against Multimodal Encoders","created":"2022-09-30","cited_by_count":41,"area":"safety"},{"id":"2209.12269","title":"Algorithms that Approximate Data Removal: New Results and Limitations","created":"2022-09-25","cited_by_count":40,"area":"safety"},{"id":"2210.10750","title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","created":"2022-10-19","cited_by_count":40,"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":"2208.10836","title":"Evaluating Machine Unlearning via Epistemic Uncertainty","created":"2022-08-23","cited_by_count":39,"area":"safety"},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"area":"safety"},{"id":"2410.18057","title":"CLEAR: Character Unlearning in Textual and Visual Modalities","created":"2024-10-23","cited_by_count":39,"area":"safety"},{"id":"2310.00108","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","created":"2023-09-29","cited_by_count":38,"area":"safety"},{"id":"2207.05801","title":"RelaxLoss: Defending Membership Inference Attacks without Losing Utility","created":"2022-07-12","cited_by_count":37,"area":"safety"},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37,"area":"safety"},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37,"area":"safety"},{"id":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2106.11384","title":"Membership Inference on Word Embedding and Beyond","created":"2021-06-21","cited_by_count":35,"area":"safety"},{"id":"2405.07406","title":"Machine Unlearning: A Comprehensive Survey","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34,"area":"safety"},{"id":"2211.00463","title":"Amplifying Membership Exposure via Data Poisoning","created":"2022-11-01","cited_by_count":34,"area":"safety"},{"id":"2309.08230","title":"A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services","created":"2023-09-15","cited_by_count":34,"area":"safety"},{"id":"2105.03592","title":"De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks","created":"2021-05-08","cited_by_count":33,"area":"safety"},{"id":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2206.05199","title":"Bayesian Estimation of Differential Privacy","created":"2022-06-10","cited_by_count":33,"area":"safety"},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2211.05427","title":"On the Privacy Risks of Algorithmic Recourse","created":"2022-11-10","cited_by_count":32,"area":"safety"},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2411.11315","title":"A Review on Machine Unlearning","created":"2024-11-18","cited_by_count":32,"area":"safety"},{"id":"2103.07101","title":"On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models","created":"2021-03-12","cited_by_count":31,"area":"safety"},{"id":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29,"area":"safety"}],"next_cursor":"100"}