{"total":218,"rows":[{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878,"area":"safety"},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763,"area":null},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732,"area":"diffusion"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"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":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2101.04535","title":"Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning","created":"2021-01-11","cited_by_count":199,"area":null},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170,"area":null},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148,"area":null},{"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":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2305.08846","title":"Privacy Auditing with One (1) Training Run","created":"2023-05-15","cited_by_count":123,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2206.10341","title":"Neurotoxin: Durable Backdoors in Federated Learning","created":"2022-06-12","cited_by_count":98,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"area":"safety"},{"id":"2302.03262","title":"Membership Inference Attacks against Diffusion Models","created":"2023-02-07","cited_by_count":86,"area":"diffusion"},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83,"area":null},{"id":"2102.05855","title":"Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent","created":"2021-02-11","cited_by_count":73,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2101.11073","title":"Property Inference From Poisoning","created":"2021-01-26","cited_by_count":60,"area":null},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60,"area":null},{"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":"2108.04417","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","created":"2021-08-10","cited_by_count":58,"area":null},{"id":"2111.11343","title":"Decentralized Federated Learning through Proxy Model Sharing","created":"2021-11-22","cited_by_count":57,"area":null},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57,"area":null},{"id":"2211.06550","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","created":"2022-11-12","cited_by_count":57,"area":null},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54,"area":null},{"id":"2403.04468","title":"A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges","created":"2024-03-07","cited_by_count":54,"area":null},{"id":"2106.03408","title":"Antipodes of Label Differential Privacy: PATE and ALIBI","created":"2021-06-07","cited_by_count":52,"area":null},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51,"area":null},{"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":"2203.00949","title":"GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation","created":"2022-03-02","cited_by_count":46,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2202.12219","title":"Debugging Differential Privacy: A Case Study for Privacy Auditing","created":"2022-02-24","cited_by_count":40,"area":null},{"id":"2209.12269","title":"Algorithms that Approximate Data Removal: New Results and Limitations","created":"2022-09-25","cited_by_count":40,"area":"safety"},{"id":"2111.04683","title":"Revisiting Methods for Finding Influential Examples","created":"2021-11-08","cited_by_count":39,"area":null},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","cited_by_count":36,"area":null},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2404.17399","title":"Evaluations of Machine Learning Privacy Defenses are Misleading","created":"2024-04-26","cited_by_count":36,"area":null},{"id":"2206.05199","title":"Bayesian Estimation of Differential Privacy","created":"2022-06-10","cited_by_count":33,"area":"safety"},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2206.07737","title":"Disparate Impact in Differential Privacy from Gradient Misalignment","created":"2022-06-15","cited_by_count":31,"area":null},{"id":"2208.12348","title":"SNAP: Efficient Extraction of Private Properties with Poisoning","created":"2022-08-25","cited_by_count":31,"area":null},{"id":"2410.22235","title":"Auditing $f$-Differential Privacy in One Run","created":"2024-10-29","cited_by_count":30,"area":null},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2407.07737","title":"Fine-Tuning Large Language Models with User-Level Differential Privacy","created":"2024-07-10","cited_by_count":29,"area":null},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27,"area":null},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27,"area":null},{"id":"2203.16828","title":"Rethinking Portrait Matting with Privacy Preserving","created":"2022-03-31","cited_by_count":25,"area":null},{"id":"2210.08643","title":"A General Framework for Auditing Differentially Private Machine Learning","created":"2022-10-16","cited_by_count":25,"area":null},{"id":"2210.02912","title":"CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2301.10053","title":"A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data","created":"2023-01-24","cited_by_count":24,"area":null},{"id":"2106.04590","title":"PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2209.14987","title":"No Free Lunch in \"Privacy for Free: How does Dataset Condensation Help Privacy\"","created":"2022-09-29","cited_by_count":23,"area":null},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2308.16375","title":"A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications","created":"2023-08-31","cited_by_count":22,"area":null},{"id":"2404.00473","title":"Privacy Backdoors: Stealing Data with Corrupted Pretrained Models","created":"2024-03-30","cited_by_count":22,"area":null},{"id":"2306.07273","title":"Gaussian Membership Inference Privacy","created":"2023-06-12","cited_by_count":21,"area":"safety"},{"id":"2405.14106","title":"Nearly Tight Black-Box Auditing of Differentially Private Machine Learning","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2206.02617","title":"Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent","created":"2022-06-06","cited_by_count":20,"area":null},{"id":"2305.18447","title":"Unleashing the Power of Randomization in Auditing Differentially Private ML","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2405.14457","title":"Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2210.13662","title":"Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2312.05140","title":"Membership Inference Attacks on Diffusion Models via Quantile Regression","created":"2023-12-08","cited_by_count":17,"area":"diffusion"},{"id":"2402.09477","title":"PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining","created":"2024-02-12","cited_by_count":17,"area":"safety"},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2202.11823","title":"Differentially Private Speaker Anonymization","created":"2022-02-23","cited_by_count":16,"area":null},{"id":"2308.10888","title":"Unlocking Accuracy and Fairness in Differentially Private Image Classification","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2202.12232","title":"Bounding Membership Inference","created":"2022-02-24","cited_by_count":15,"area":"safety"},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2312.05114","title":"The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against \"Truly Anonymous\" Synthetic Datasets","created":"2023-12-08","cited_by_count":14,"area":null},{"id":"2304.10819","title":"Auditing and Generating Synthetic Data with Controllable Trust Trade-offs","created":"2023-04-21","cited_by_count":13,"area":null},{"id":"2406.13985","title":"The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2209.04030","title":"Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks","created":"2022-09-08","cited_by_count":12,"area":null},{"id":"2304.08928","title":"ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees","created":"2023-04-18","cited_by_count":12,"area":null},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2304.07927","title":"A Randomized Approach for Tight Privacy Accounting","created":"2023-04-17","cited_by_count":11,"area":null},{"id":"2307.00310","title":"Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD","created":"2023-07-01","cited_by_count":11,"area":null},{"id":"2410.06186","title":"The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD","created":"2024-10-08","cited_by_count":11,"area":null},{"id":"2503.14681","title":"DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2407.06496","title":"It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss","created":"2024-07-09","cited_by_count":10,"area":null},{"id":"2306.05093","title":"Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2306.13054","title":"Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems","created":"2023-06-22","cited_by_count":9,"area":null},{"id":"2412.08559","title":"Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning","created":"2024-12-11","cited_by_count":9,"area":"safety"},{"id":"2503.07199","title":"How Well Can Differential Privacy Be Audited in One Run?","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2205.06369","title":"How to Combine Membership-Inference Attacks on Multiple Updated Models","created":"2022-05-12","cited_by_count":8,"area":"safety"},{"id":"2501.03941","title":"Synthetic Data Privacy Metrics","created":"2025-01-07","cited_by_count":8,"area":null},{"id":"2208.08662","title":"Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy","created":"2022-08-18","cited_by_count":7,"area":null},{"id":"2402.03688","title":"A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective","created":"2024-02-06","cited_by_count":7,"area":null}],"next_cursor":"100"}