Privacy

Unsupervised Text Deidentification EMNLP 2022 Utility Preservation of Clinical Text After De-Identification ACL 2022 Verifying Hardware Security Modules with Information-Preserving Refinement OSDI 2022 VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models NeurIPS 2022 You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas NAACL 2022 A Backdoor Attack Against 3D Point Cloud Classifiers ICCV 2021 Addressing Compliance in Call Centers with Entity Extraction Interspeech 2021 Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation Interspeech 2021 Against Membership Inference Attack: Pruning is All You Need IJCAI 2021 An Initial Investigation for Detecting Partially Spoofed Audio Interspeech 2021 Anonymizing Egocentric Videos ICCV 2021 A Secure and Efficient Federated Learning Framework for NLP EMNLP 2021 Attacks against Ranking Algorithms with Text Embeddings: A Case Study on Recruitment Algorithms EMNLP 2021 Backdoor Attacks Against Deep Learning Systems in the Physical World CVPR 2021 Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification ICLR 2021 Configurable Privacy-Preserving Automatic Speech Recognition Interspeech 2021 CRFL: Certifiably Robust Federated Learning against Backdoor Attacks ICML 2021 CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRU EMNLP 2021 Data-Free Model Extraction CVPR 2021 Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification AAAI 2021 Ensemble Attention Distillation for Privacy-Preserving Federated Learning ICCV 2021 Federated Learning of User Verification Models Without Sharing Embeddings ICML 2021 Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix ICML 2021 Grey-box Extraction of Natural Language Models ICML 2021 HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture ICML 2021