differential privacy

Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs AAAI 2026 Unintended Memorization of Sensitive Information in Fine-Tuned Language Models EACL 2026 Venom: Liquid Diffusion-Guided Gradient Inversion for Breaking Differential Privacy in Federated Learning AAAI 2026 Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration UAI 2026 A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets AISTATS 2025 Adaptive Batch Size for Privately Finding Second-Order Stationary Points ICLR 2025 AI-Driven Personalized Fall Prevention for Older Adults AAAI 2025 Almost linear time differentially private release of synthetic graphs AISTATS 2025 A New Federated Learning Framework Against Gradient Inversion Attacks AAAI 2025 Auditing f-differential privacy in one run ICML 2025 Balls-and-Bins Sampling for DP-SGD AISTATS 2025 Best Linear Unbiased Estimate from Privatized Contingency Tables JMLR 2025 Better Private Distribution Testing by Leveraging Unverified Auxiliary Data COLT 2025 Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation EMNLP 2025 Can Private Machine Learning Be Fair? AAAI 2025 Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy ICML 2025 Certification for Differentially Private Prediction in Gradient-Based Training ICML 2025 Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization AISTATS 2025 Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off ICML 2025 CluSanT: Differentially Private and Semantically Coherent Text Sanitization NAACL 2025 Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion ICML 2025 Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning ICLR 2025 Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy COLT 2025 Differentially private algorithms for linear queries via stochastic convex optimization AISTATS 2025 Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference ICML 2025