Security & Privacy

Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy EMNLP 2021 Instance-optimal Mean Estimation Under Differential Privacy NeurIPS 2021 IronMask: Modular Architecture for Protecting Deep Face Template CVPR 2021 Knowledge-Enriched Distributional Model Inversion Attacks ICCV 2021 Label-Only Membership Inference Attacks ICML 2021 Large-Capacity Image Steganography Based on Invertible Neural Networks CVPR 2021 LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy IJCAI 2021 Learner-Private Convex Optimization ICML 2021 Learning and Evaluating a Differentially Private Pre-trained Language Model EMNLP 2021 Learning Model-Based Privacy Protection under Budget Constraints AAAI 2021 Leveraging Public Data for Practical Private Query Release ICML 2021 Locally Differentially-Private Randomized Response for Discrete Distribution Learning JMLR 2021 Lossless Compression of Efficient Private Local Randomizers ICML 2021 Machine Unlearning via Algorithmic Stability COLT 2021 Manipulating SGD with Data Ordering Attacks NeurIPS 2021 MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation CVPR 2021 Measuring data leakage in machine-learning models with Fisher information UAI 2021 Membership Inference Attacks Are Easier on Difficult Problems ICCV 2021 Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer EMNLP 2021 Mitigating Data Poisoning in Text Classification with Differential Privacy EMNLP 2021 Modeling Deep Learning Based Privacy Attacks on Physical Mail AAAI 2021 Multiclass versus Binary Differentially Private PAC Learning NeurIPS 2021 (Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces COLT 2021 Non-Euclidean Differentially Private Stochastic Convex Optimization COLT 2021 Oneshot Differentially Private Top-k Selection ICML 2021