Privacy

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces NeurIPS 2023 Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information EACL 2023 GPTs Don’t Keep Secrets: Searching for Backdoor Watermark Triggers in Autoregressive Language Models ACL 2023 Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy NeurIPS 2023 Graph Generative Model for Benchmarking Graph Neural Networks ICML 2023 GuardHFL: Privacy Guardian for Heterogeneous Federated Learning ICML 2023 Guiding Text-to-Text Privatization by Syntax ACL 2023 Have it your way: Individualized Privacy Assignment for DP-SGD NeurIPS 2023 HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption ICML 2023 Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks NeurIPS 2023 HiddenTables and PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies EMNLP 2023 High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent AISTATS 2023 How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023 How to Backdoor Diffusion Models? CVPR 2023 IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ACL 2023 Improving the Model Consistency of Decentralized Federated Learning ICML 2023 Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners NeurIPS 2023 Incentive-Boosted Federated Crowdsourcing AAAI 2023 Incentives in Private Collaborative Machine Learning NeurIPS 2023 Incentivising Diffusion while Preserving Differential Privacy UAI 2023 Incentivized Communication for Federated Bandits NeurIPS 2023 INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization EACL 2023 Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks ICLR 2023 Industry-Scale Orchestrated Federated Learning for Drug Discovery AAAI 2023 Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks NeurIPS 2023