Security & Privacy

Revisiting Injective Attacks on Recommender Systems NeurIPS 2022 Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models ICLR 2022 Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification AAAI 2022 Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy NeurIPS 2022 Secure Quantized Training for Deep Learning ICML 2022 Selective Differential Privacy for Language Modeling NAACL 2022 Sentence-level Privacy for Document Embeddings ACL 2022 Shape And Structure Preserving Differential Privacy NeurIPS 2022 Shuffle Private Stochastic Convex Optimization ICLR 2022 SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression NeurIPS 2022 Spectrum: High-bandwidth Anonymous Broadcast NSDI 2022 Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs COLING 2022 Subspace Differential Privacy AAAI 2022 Task-level Differentially Private Meta Learning NeurIPS 2022 TextFusion: Privacy-Preserving Pre-trained Model Inference via Token Fusion EMNLP 2022 The CLIPS System for 2022 Spoofing-Aware Speaker Verification Challenge Interspeech 2022 THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption ACL 2022 Tight and Robust Private Mean Estimation with Few Users ICML 2022 Toward Privacy-preserving Text Embedding Similarity with Homomorphic Encryption EMNLP 2022 Towards Efficient Data Free Black-Box Adversarial Attack CVPR 2022 Transfer Learning In Differential Privacy’s Hybrid-Model ICML 2022 Triggerless Backdoor Attack for NLP Tasks with Clean Labels NAACL 2022 Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector Interspeech 2022 Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy ICML 2022 Unsupervised Text Deidentification EMNLP 2022