{"total":114,"rows":[{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180,"area":null},{"id":"2102.06062","title":"Deep Learning with Label Differential Privacy","created":"2021-02-11","cited_by_count":117,"area":null},{"id":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","cited_by_count":88,"area":null},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84,"area":null},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68,"area":null},{"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":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65,"area":null},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2210.00036","title":"Differentially Private Bias-Term Fine-tuning of Foundation Models","created":"2022-09-30","cited_by_count":48,"area":null},{"id":"2203.05816","title":"No Free Lunch Theorem for Security and Utility in Federated Learning","created":"2022-03-11","cited_by_count":39,"area":null},{"id":"2210.15042","title":"Privately Fine-Tuning Large Language Models with Differential Privacy","created":"2022-10-26","cited_by_count":39,"area":null},{"id":"2105.00529","title":"GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning","created":"2021-05-02","cited_by_count":36,"area":null},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36,"area":null},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36,"area":null},{"id":"2106.12576","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?","created":"2021-06-22","cited_by_count":33,"area":null},{"id":"2110.14153","title":"Differentially Private Federated Bayesian Optimization with Distributed Exploration","created":"2021-10-27","cited_by_count":32,"area":null},{"id":"2103.07567","title":"Privacy Regularization: Joint Privacy-Utility Optimization in Language Models","created":"2021-03-12","cited_by_count":30,"area":null},{"id":"2111.00173","title":"Dynamic Differential-Privacy Preserving SGD","created":"2021-10-30","cited_by_count":30,"area":null},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2102.11158","title":"Federated $f$-Differential Privacy","created":"2021-02-22","cited_by_count":29,"area":null},{"id":"2103.11003","title":"Differentially private inference via noisy optimization","created":"2021-03-19","cited_by_count":27,"area":null},{"id":"2112.06872","title":"Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors","created":"2021-12-13","cited_by_count":25,"area":null},{"id":"2401.17319","title":"Decentralized Federated Learning: A Survey on Security and Privacy","created":"2024-01-25","cited_by_count":25,"area":null},{"id":"2106.09680","title":"Accuracy, Interpretability, and Differential Privacy via Explainable Boosting","created":"2021-06-17","cited_by_count":24,"area":null},{"id":"2310.18574","title":"Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning","created":"2023-10-28","cited_by_count":22,"area":"safety"},{"id":"2307.10655","title":"A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency","created":"2023-07-20","cited_by_count":21,"area":null},{"id":"2102.12412","title":"Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT","created":"2021-02-24","cited_by_count":20,"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":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20,"area":null},{"id":"2302.02589","title":"$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning","created":"2023-02-06","cited_by_count":17,"area":null},{"id":"2105.08233","title":"Oneshot Differentially Private Top-k Selection","created":"2021-05-18","cited_by_count":16,"area":null},{"id":"2207.04381","title":"Faster Privacy Accounting via Evolving Discretization","created":"2022-07-10","cited_by_count":15,"area":null},{"id":"2307.03928","title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","created":"2023-07-08","cited_by_count":15,"area":null},{"id":"2206.04236","title":"Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2109.13012","title":"Federated Deep Learning with Bayesian Privacy","created":"2021-09-27","cited_by_count":13,"area":null},{"id":"2310.19973","title":"Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy","created":"2023-10-30","cited_by_count":13,"area":null},{"id":"2403.00278","title":"Shifted Interpolation for Differential Privacy","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2204.03230","title":"What You See is What You Get: Principled Deep Learning via Distributional Generalization","created":"2022-04-07","cited_by_count":11,"area":null},{"id":"2304.07927","title":"A Randomized Approach for Tight Privacy Accounting","created":"2023-04-17","cited_by_count":11,"area":null},{"id":"2103.14068","title":"Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2108.10623","title":"Data-Free Evaluation of User Contributions in Federated Learning","created":"2021-08-24","cited_by_count":10,"area":null},{"id":"2311.14056","title":"DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release","created":"2023-11-23","cited_by_count":10,"area":"safety"},{"id":"2102.10875","title":"On the robustness of randomized classifiers to adversarial examples","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2311.16065","title":"A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2402.16515","title":"LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification","created":"2024-02-26","cited_by_count":8,"area":"distill"},{"id":"2402.18752","title":"Pre-training Differentially Private Models with Limited Public Data","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2405.08920","title":"Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2409.09558","title":"A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem","created":"2024-09-14","cited_by_count":8,"area":null},{"id":"2112.14430","title":"DP-FP: Differentially Private Forward Propagation for Large Models","created":"2021-12-29","cited_by_count":7,"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":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2310.19215","title":"On the accuracy and efficiency of group-wise clipping in differentially private optimization","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2311.11822","title":"Zero redundancy distributed learning with differential privacy","created":"2023-11-20","cited_by_count":7,"area":null},{"id":"2503.00703","title":"Towards hyperparameter-free optimization with differential privacy","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2107.08461","title":"Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability","created":"2021-07-18","cited_by_count":6,"area":null},{"id":"2211.08942","title":"Differentially Private Optimizers Can Learn Adversarially Robust Models","created":"2022-11-16","cited_by_count":6,"area":null},{"id":"2503.10945","title":"Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2510.13094","title":"Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach","created":"2025-10-15","cited_by_count":6,"area":"safety"},{"id":"2110.02329","title":"Task-aware Privacy Preservation for Multi-dimensional Data","created":"2021-10-05","cited_by_count":5,"area":null},{"id":"2110.07435","title":"Adaptive Differentially Private Empirical Risk Minimization","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2209.11531","title":"Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy","created":"2022-09-23","cited_by_count":5,"area":null},{"id":"2307.01875","title":"Approximate, Adapt, Anonymize (3A): a Framework for Privacy Preserving Training Data Release for Machine Learning","created":"2023-07-04","cited_by_count":5,"area":null},{"id":"2106.11767","title":"Privacy Amplification via Iteration for Shuffled and Online PNSGD","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2202.05089","title":"Backpropagation Clipping for Deep Learning with Differential Privacy","created":"2022-02-10","cited_by_count":4,"area":null},{"id":"2206.07125","title":"Self-Supervised Pretraining for Differentially Private Learning","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2305.04095","title":"Gradient Leakage Defense with Key-Lock Module for Federated Learning","created":"2023-05-06","cited_by_count":4,"area":null},{"id":"2405.13746","title":"CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2410.09296","title":"The 2020 US Decennial Census is more private than you (might) think","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2601.10237","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2110.11578","title":"PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy","created":"2021-10-22","cited_by_count":3,"area":null},{"id":"2110.12770","title":"DP-XGBoost: Private Machine Learning at Scale","created":"2021-10-25","cited_by_count":3,"area":null},{"id":"2209.04445","title":"Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2302.09624","title":"Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2310.01304","title":"Coupling public and private gradient provably helps optimization","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2402.15603","title":"Differentially Private Fair Binary Classifications","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2603.22563","title":"Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling","created":"2026-03-23","cited_by_count":3,"area":"alignment"},{"id":"2104.01987","title":"Rejoinder: Gaussian Differential Privacy","created":"2021-04-05","cited_by_count":2,"area":null},{"id":"2110.08676","title":"Noise-Augmented Privacy-Preserving Empirical Risk Minimization with Dual-purpose Regularizer and Privacy Budget Retrieval and Recycling","created":"2021-10-16","cited_by_count":2,"area":null},{"id":"2202.06467","title":"NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2203.07728","title":"Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2302.05787","title":"Differentially Private Normalizing Flows for Density Estimation, Data Synthesis, and Variational Inference with Application to Electronic Health Records","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2305.15165","title":"Personalized DP-SGD using Sampling Mechanisms","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.03792","title":"PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2410.08734","title":"Gradients Stand-in for Defending Deep Leakage in Federated Learning","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2507.20560","title":"Statistical Inference for Differentially Private Stochastic Gradient Descent","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2109.10528","title":"A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index","created":"2021-09-22","cited_by_count":1,"area":null},{"id":"2205.12718","title":"DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Pooling","created":"2022-05-24","cited_by_count":1,"area":null},{"id":"2209.04419","title":"Majority Vote for Distributed Differentially Private Sign Selection","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2212.01688","title":"LDL: A Defense for Label-Based Membership Inference Attacks","created":"2022-12-03","cited_by_count":1,"area":"safety"},{"id":"2303.09527","title":"Fairness-aware Differentially Private Collaborative Filtering","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2312.13389","title":"Enhancing Trade-offs in Privacy, Utility, and Computational Efficiency through MUltistage Sampling Technique (MUST)","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2312.16554","title":"A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2404.12730","title":"PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2503.21154","title":"Federated Learning with Differential Privacy: An Utility-Enhanced Approach","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2510.01447","title":"SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2605.06259","title":"Trade-off Functions for DP-SGD with Subsampling based on Random Allocation: Tight Upper and Lower Bounds","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.07674","title":"Differentially Private Auditing Under Strategic Response","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2210.00053","title":"Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2309.10965","title":"DPpack: An R Package for Differentially Private Statistical Analysis and Machine Learning","created":"2023-09-19","cited_by_count":0,"area":null}],"next_cursor":"100"}