privacy guarantee

A Certified Unlearning Approach without Access to Source Data ICML 2025 Improving the Variance of Differentially Private Randomized Experiments through Clustering ICML 2025 Private Synthetic Text Generation with Diffusion Models NAACL 2025 Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model ICLR 2025 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024 Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning NeurIPS 2024 Optimal Learning Policies for Differential Privacy in Multi-armed Bandits JMLR 2024 Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains AISTATS 2024 Scalable DP-SGD: Shuffling vs. Poisson Subsampling NeurIPS 2024 Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks AAAI 2024 Does Label Differential Privacy Prevent Label Inference Attacks? AISTATS 2023 Easy Differentially Private Linear Regression ICLR 2023 Forget Unlearning: Towards True Data-Deletion in Machine Learning ICML 2023 Gaussian Membership Inference Privacy NeurIPS 2023 Improved Convergence of Differential Private SGD with Gradient Clipping ICLR 2023 Nearly Tight Bounds For Differentially Private Multiway Cut NeurIPS 2023 Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning NeurIPS 2023 Privacy-Aware Rejection Sampling JMLR 2023 Unbounded Differentially Private Quantile and Maximum Estimation NeurIPS 2023 Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space ICLR 2022 Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy NeurIPS 2022 Near-Optimal Correlation Clustering with Privacy NeurIPS 2022 One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022 PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning ICLR 2022 Privacy Implications of Shuffling ICLR 2022