Differential Privacy

Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022 In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning NeurIPS 2022 Iron: Private Inference on Transformers NeurIPS 2022 Just Fine-tune Twice: Selective Differential Privacy for Large Language Models EMNLP 2022 Kantorovich Mechanism for Pufferfish Privacy AISTATS 2022 Label differential privacy via clustering AISTATS 2022 Large Language Models Can Be Strong Differentially Private Learners ICLR 2022 Large-Scale Differentially Private BERT EMNLP 2022 Local Differential Privacy for Belief Functions AAAI 2022 Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes ACML 2022 Locally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error AAAI 2022 Log-Concave and Multivariate Canonical Noise Distributions for Differential Privacy NeurIPS 2022 Momentum Aggregation for Private Non-convex ERM NeurIPS 2022 Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging NeurIPS 2022 (Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping COLT 2022 Near-Optimal Correlation Clustering with Privacy NeurIPS 2022 One-bit Submission for Locally Private Quasi-MLE: Its Asymptotic Normality and Limitation AISTATS 2022 One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022 On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data ACML 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022 Optimal Accounting of Differential Privacy via Characteristic Function AISTATS 2022 Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits AISTATS 2022 Parametric Bootstrap for Differentially Private Confidence Intervals AISTATS 2022 Privacy Amplification by Decentralization AISTATS 2022 Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation NeurIPS 2022