Privacy

Free-rider Attacks on Model Aggregation in Federated Learning AISTATS 2021 Game of Gradients: Mitigating Irrelevant Clients in Federated Learning AAAI 2021 Generalized Linear Bandits with Local Differential Privacy NeurIPS 2021 Goten: GPU-Outsourcing Trusted Execution of Neural Network Training AAAI 2021 G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators NeurIPS 2021 Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix ICML 2021 Gradient Inversion with Generative Image Prior NeurIPS 2021 Graph-Free Knowledge Distillation for Graph Neural Networks IJCAI 2021 GraphMI: Extracting Private Graph Data from Graph Neural Networks IJCAI 2021 Grey-box Extraction of Natural Language Models ICML 2021 Harnessing Social Media to Identify Homeless Youth At-Risk of Substance Use AAAI 2021 HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture ICML 2021 Hiding Numerical Vectors in Local Private and Shuffled Messages IJCAI 2021 How Does Data Augmentation Affect Privacy in Machine Learning? AAAI 2021 How effective is BERT without word ordering? Implications for language understanding and data privacy ACL 2021 Improving Fairness and Privacy in Selection Problems AAAI 2021 Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy EMNLP 2021 Improving Robustness to Model Inversion Attacks via Mutual Information Regularization AAAI 2021 Improving the Performance-Compatibility Tradeoff with Personalized Objective Functions AAAI 2021 Individual Privacy Accounting via a Rényi Filter NeurIPS 2021 Information Obfuscation of Graph Neural Networks ICML 2021 Instance-optimal Mean Estimation Under Differential Privacy NeurIPS 2021 Integrative High Dimensional Multiple Testing with Heterogeneity under Data Sharing Constraints JMLR 2021 Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks AAAI 2021 InverseNet: Augmenting Model Extraction Attacks with Training Data Inversion IJCAI 2021