{"total":100,"rows":[{"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":"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":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"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":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61,"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":"2112.00193","title":"Public Data-Assisted Mirror Descent for Private Model Training","created":"2021-12-01","cited_by_count":49,"area":null},{"id":"2401.10371","title":"Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning","created":"2024-01-18","cited_by_count":49,"area":"safety"},{"id":"2203.05363","title":"Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)","created":"2022-03-10","cited_by_count":48,"area":null},{"id":"2302.10249","title":"Faster high-accuracy log-concave sampling via algorithmic warm starts","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2111.15521","title":"Node-Level Differentially Private Graph Neural Networks","created":"2021-11-23","cited_by_count":43,"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":"2102.05274","title":"Stability of SGD: Tightness Analysis and Improved Bounds","created":"2021-02-10","cited_by_count":33,"area":null},{"id":"2206.05091","title":"Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging","created":"2022-06-10","cited_by_count":27,"area":null},{"id":"2506.06985","title":"Certified Unlearning for Neural Networks","created":"2025-06-08","cited_by_count":27,"area":"safety"},{"id":"2401.17319","title":"Decentralized Federated Learning: A Survey on Security and Privacy","created":"2024-01-25","cited_by_count":25,"area":null},{"id":"2103.07073","title":"DP-Image: Differential Privacy for Image Data in Feature Space","created":"2021-03-12","cited_by_count":23,"area":null},{"id":"2206.00363","title":"Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization","created":"2022-06-01","cited_by_count":22,"area":null},{"id":"2210.08448","title":"Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling","created":"2022-10-16","cited_by_count":22,"area":null},{"id":"2403.17673","title":"How Private are DP-SGD Implementations?","created":"2024-03-26","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":"2103.15352","title":"Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps","created":"2021-03-29","cited_by_count":21,"area":null},{"id":"2110.02159","title":"Label differential privacy via clustering","created":"2021-10-05","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":"2310.15526","title":"Privacy Amplification for Matrix Mechanisms","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2411.04205","title":"Scalable DP-SGD: Shuffling vs. Poisson Subsampling","created":"2024-11-06","cited_by_count":16,"area":null},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15,"area":null},{"id":"2311.14632","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","created":"2023-11-24","cited_by_count":14,"area":null},{"id":"2403.17105","title":"Certified Machine Unlearning via Noisy Stochastic Gradient Descent","created":"2024-03-25","cited_by_count":14,"area":"safety"},{"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":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"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":"2107.01561","title":"Certifiably Robust Interpretation via Renyi Differential Privacy","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2210.06328","title":"Momentum Aggregation for Private Non-convex ERM","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2305.09903","title":"Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses","created":"2023-05-17","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":"2402.07471","title":"Differentially Private Decentralized Learning with Random Walks","created":"2024-02-12","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":"2410.01068","title":"Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2203.03604","title":"Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms","created":"2022-03-07","cited_by_count":6,"area":null},{"id":"2407.05237","title":"Privacy of the last iterate in cyclically-sampled DP-SGD on nonconvex composite losses","created":"2024-07-07","cited_by_count":6,"area":null},{"id":"2411.10614","title":"To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling","created":"2024-11-15","cited_by_count":6,"area":null},{"id":"2302.12559","title":"From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning","created":"2023-02-24","cited_by_count":5,"area":null},{"id":"2410.22699","title":"Exactly Minimax-Optimal Locally Differentially Private Sampling","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2506.16666","title":"The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing","created":"2025-06-20","cited_by_count":5,"area":null},{"id":"2105.10594","title":"Privacy Amplification Via Bernoulli Sampling","created":"2021-05-21","cited_by_count":4,"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":"2210.03843","title":"Differentially Private Deep Learning with ModelMix","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2310.14661","title":"Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy","created":"2023-10-23","cited_by_count":4,"area":null},{"id":"2407.00077","title":"Differentially Private Graph Diffusion with Applications in Personalized PageRanks","created":"2024-06-22","cited_by_count":4,"area":null},{"id":"2502.17772","title":"An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.18786","title":"Leveraging Per-Instance Privacy for Machine Unlearning","created":"2025-05-24","cited_by_count":4,"area":"safety"},{"id":"2204.01585","title":"Differentially Private Sampling from Rashomon Sets, and the Universality of Langevin Diffusion for Convex Optimization","created":"2022-04-04","cited_by_count":3,"area":null},{"id":"2212.03080","title":"Straggler-Resilient Differentially-Private Decentralized Learning","created":"2022-12-06","cited_by_count":3,"area":null},{"id":"2403.17572","title":"Enhancing Privacy in Federated Learning through Local Training","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2510.19934","title":"Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy","created":"2025-10-22","cited_by_count":3,"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":"2312.13985","title":"R\\'enyi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2401.10294","title":"Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2402.08344","title":"Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2403.13041","title":"Provable Privacy with Non-Private Pre-Processing","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2407.04884","title":"Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2408.01040","title":"Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix","created":"2024-08-02","cited_by_count":2,"area":"safety"},{"id":"2501.12046","title":"Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2503.21071","title":"Purifying Approximate Differential Privacy with Randomized Post-processing","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2506.05101","title":"Privacy Amplification Through Synthetic Data: Insights from Linear Regression","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2106.12959","title":"Differentially Private Algorithms for Clustering with Stability Assumptions","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2210.01864","title":"Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2312.08685","title":"Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2404.08847","title":"LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models","created":"2024-04-12","cited_by_count":1,"area":null},{"id":"2504.21634","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2507.01487","title":"How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2510.07304","title":"Cocoon: A System Architecture for Differentially Private Training with Correlated Noises","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.23463","title":"Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.08443","title":"Fully Decentralized Certified Unlearning","created":"2025-12-09","cited_by_count":1,"area":"safety"},{"id":"2603.00342","title":"Challenges in Enabling Private Data Valuation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2211.02003","title":"Private Blind Model Averaging - Distributed, Non-interactive, and Convergent","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2303.16372","title":"On the Query Complexity of Training Data Reconstruction in Private Learning","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2406.13183","title":"Communication-Efficient and Privacy-Preserving Decentralized Meta-Learning","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2407.08233","title":"Differentially Private Neural Network Training Under the Hidden State Assumption","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2412.01756","title":"Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2501.04134","title":"Mixing Times and Privacy Analysis for the Projected Langevin Algorithm under a Modulus of Continuity","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2504.16000","title":"How Private is Your Attention? Bridging Privacy with In-Context Learning","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2505.14323","title":"Securing Transfer-Learned Networks with Reverse Homomorphic Encryption","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.00158","title":"Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2509.25906","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.15634","title":"R\\'enyi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincar\\'e Inequalities","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2512.00307","title":"Adversarial Signed Graph Learning with Differential Privacy","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.05134","title":"Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning","created":"2026-01-08","cited_by_count":0,"area":"safety"},{"id":"2602.04895","title":"Privacy Amplification Persists under Unlimited Synthetic Data Release","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.15602","title":"Certified Per-Instance Unlearning Using Individual Sensitivity Bounds","created":"2026-02-17","cited_by_count":0,"area":"safety"},{"id":"2603.19040","title":"When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2606.03033","title":"Local and Global Contraction Principles for MCMC Mixing","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2610.02716","title":"Differential Privacy of Gradient Descent on Perturbed Objectives","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.17120","title":"Can R\\'enyi Accountants Beat Lossless Accountants for DP-SGD?","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17993","title":"Counterfactual Certification for Sequential Unlearning with Long-Run Performance Guarantees","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}