Privacy

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing NeurIPS 2022 Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples NeurIPS 2022 Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation EMNLP 2022 Encrypted Linear Contextual Bandit AISTATS 2022 End-to-end speech recognition modeling from de-identified data Interspeech 2022 Enhancing Speech Privacy with Slicing Interspeech 2022 Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis MLHC 2022 Estimating Causal Effects under Network Interference with Bayesian Generalized Propensity Scores JMLR 2022 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 Extracting Targeted Training Data from ASR Models, and How to Mitigate It Interspeech 2022 Fair NLP Models with Differentially Private Text Encoders EMNLP 2022 Faster Privacy Accounting via Evolving Discretization ICML 2022 Faster Rates of Private Stochastic Convex Optimization ALT 2022 FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning IJCAI 2022 Federated Learning for Face Recognition with Gradient Correction AAAI 2022 Federated Learning with Buffered Asynchronous Aggregation AISTATS 2022 Federated Learning with Noisy User Feedback NAACL 2022 Federated Model Decomposition with Private Vocabulary for Text Classification EMNLP 2022 Federated Pruning: Improving Neural Network Efficiency with Federated Learning Interspeech 2022 FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition AAAI 2022 FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning ICML 2022 Few-Shot Backdoor Defense Using Shapley Estimation CVPR 2022 Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022 Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022 Fixed Neural Network Steganography: Train the images, not the network ICLR 2022