Security & Privacy

FLVoogd: Robust And Privacy Preserving Federated Learning ACML 2022 FriendlyCore: Practical Differentially Private Aggregation ICML 2022 Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack NeurIPS 2022 Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs IJCAI 2022 GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022 How reparametrization trick broke differentially-private text representation learning ACL 2022 Hyperparameter Tuning with Renyi Differential Privacy ICLR 2022 Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy NeurIPS 2022 Image Disentanglement Autoencoder for Steganography Without Embedding CVPR 2022 Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022 Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams NeurIPS 2022 Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data ICML 2022 Improved Regret for Differentially Private Exploration in Linear MDP ICML 2022 Improved Utility Analysis of Private CountSketch NeurIPS 2022 Incorporating Item Frequency for Differentially Private Set Union AAAI 2022 Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022 In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning NeurIPS 2022 Invernet: An Inversion Attack Framework to Infer Fine-Tuning Datasets through Word Embeddings EMNLP 2022 Iron: Private Inference on Transformers NeurIPS 2022 Just Fine-tune Twice: Selective Differential Privacy for Large Language Models EMNLP 2022 Justitia: Software Multi-Tenancy in Hardware Kernel-Bypass Networks NSDI 2022 Kantorovich Mechanism for Pufferfish Privacy AISTATS 2022 Label differential privacy via clustering AISTATS 2022 LAMP: Extracting Text from Gradients with Language Model Priors NeurIPS 2022 Large Language Models Can Be Strong Differentially Private Learners ICLR 2022