{"total":199,"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":"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":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195,"area":null},{"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":"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":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128,"area":null},{"id":"2305.08846","title":"Privacy Auditing with One (1) Training Run","created":"2023-05-15","cited_by_count":123,"area":null},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107,"area":"safety"},{"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":"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":"2102.05855","title":"Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent","created":"2021-02-11","cited_by_count":73,"area":null},{"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":"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":"2109.08045","title":"Membership Inference Attacks Against Recommender Systems","created":"2021-09-16","cited_by_count":57,"area":"safety"},{"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":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"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":"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":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"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":"2206.07284","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","created":"2022-06-15","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":"2309.05610","title":"Privacy Side Channels in Machine Learning Systems","created":"2023-09-11","cited_by_count":40,"area":null},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38,"area":null},{"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":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","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":"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":"2206.05199","title":"Bayesian Estimation of Differential Privacy","created":"2022-06-10","cited_by_count":33,"area":"safety"},{"id":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31,"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":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"id":"2410.22235","title":"Auditing $f$-Differential Privacy in One Run","created":"2024-10-29","cited_by_count":30,"area":null},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27,"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":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","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":"2403.15638","title":"Differentially Private Next-Token Prediction of Large Language Models","created":"2024-03-22","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":"2204.06106","title":"Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms","created":"2022-04-12","cited_by_count":19,"area":"safety"},{"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":"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":"2303.12247","title":"Exploring the Benefits of Visual Prompting in Differential Privacy","created":"2023-03-22","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":"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":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2507.06969","title":"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy","created":"2025-07-09","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":"2406.13985","title":"The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2205.03105","title":"LPGNet: Link Private Graph Networks for Node Classification","created":"2022-05-06","cited_by_count":12,"area":null},{"id":"2207.01991","title":"Conflicting Interactions Among Protection Mechanisms for Machine Learning Models","created":"2022-07-05","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":"2311.06888","title":"Preserving Node-level Privacy in Graph Neural Networks","created":"2023-11-12","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":"2506.13972","title":"Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2202.10517","title":"Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees","created":"2022-02-21","cited_by_count":10,"area":null},{"id":"2306.03962","title":"PILLAR: How to make semi-private learning more effective","created":"2023-06-06","cited_by_count":10,"area":null},{"id":"2402.18726","title":"Unveiling Privacy, Memorization, and Input Curvature Links","created":"2024-02-28","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":"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":"2205.06369","title":"How to Combine Membership-Inference Attacks on Multiple Updated Models","created":"2022-05-12","cited_by_count":8,"area":"safety"},{"id":"2407.02191","title":"Attack-Aware Noise Calibration for Differential Privacy","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2501.03941","title":"Synthetic Data Privacy Metrics","created":"2025-01-07","cited_by_count":8,"area":null},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2411.05743","title":"Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods","created":"2024-11-08","cited_by_count":7,"area":"safety"}],"next_cursor":"100"}