Privacy

NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning CVPR 2022 Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization ICLR 2022 Not All Poisons are Created Equal: Robust Training against Data Poisoning ICML 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 Facility Location Problem in the Local Differential Privacy Model AISTATS 2022 On Learning and Refutation in Noninteractive Local Differential Privacy NeurIPS 2022 On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data ACML 2022 On Privacy and Personalization in Cross-Silo Federated Learning NeurIPS 2022 On the Difficulty of Defending Self-Supervised Learning against Model Extraction ICML 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022 Open Problem: Do you pay for Privacy in Online learning? COLT 2022 Optimal Accounting of Differential Privacy via Characteristic Function AISTATS 2022 Optimal Algorithms for Mean Estimation under Local Differential Privacy ICML 2022 Optimal Compression of Locally Differentially Private Mechanisms AISTATS 2022 Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits AISTATS 2022 Order-Invariant Cardinality Estimators Are Differentially Private NeurIPS 2022 Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling NeurIPS 2022 Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference NeurIPS 2022 Parametric Bootstrap for Differentially Private Confidence Intervals AISTATS 2022 PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning ICLR 2022 Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning ICML 2022 Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness NeurIPS 2022 Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset NeurIPS 2022 Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022