Privacy

Stability and Differential Privacy of Stochastic Gradient Descent for Pairwise Learning with Non-Smooth Loss AISTATS 2021 Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images AAAI 2021 TAG: Gradient Attack on Transformer-based Language Models EMNLP 2021 Tempered Sigmoid Activations for Deep Learning with Differential Privacy AAAI 2021 The Chinese Remainder Theorem for Compact, Task-Precise, Efficient and Secure Word Embeddings EACL 2021 The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation ICML 2021 The Skellam Mechanism for Differentially Private Federated Learning NeurIPS 2021 The Sparse Vector Technique, Revisited COLT 2021 This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models WACV 2021 Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT AISTATS 2021 Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms UAI 2021 TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation NeurIPS 2021 Towards Fair and Transparent Algorithmic Systems IJCAI 2021 Understanding Unintended Memorization in Language Models Under Federated Learning NAACL 2021 Undistillable: Making A Nasty Teacher That CANNOT teach students ICLR 2021 Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving EMNLP 2021 Unlearnable Examples: Making Personal Data Unexploitable ICLR 2021 User-Level Differentially Private Learning via Correlated Sampling NeurIPS 2021 Variational Model Inversion Attacks NeurIPS 2021 Voice Privacy Through x-Vector and CycleGAN-Based Anonymization Interspeech 2021 vqSGD: Vector Quantized Stochastic Gradient Descent AISTATS 2021 WaNet - Imperceptible Warping-based Backdoor Attack ICLR 2021 Watermarking Deep Neural Networks with Greedy Residuals ICML 2021 When differential privacy meets NLP: The devil is in the detail EMNLP 2021 When Does Data Augmentation Help With Membership Inference Attacks? ICML 2021