Privacy

Reconstruction Attack on Instance Encoding for Language Understanding EMNLP 2021 Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective ICCV 2021 SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract) AAAI 2021 See Through Gradients: Image Batch Recovery via GradInversion CVPR 2021 Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective CVPR 2021 Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images AAAI 2021 TAG: Gradient Attack on Transformer-based Language Models EMNLP 2021 The Sparse Vector Technique, Revisited COLT 2021 Towards Extracting Graph Neural Network Models via Prediction Queries (Student Abstract) AAAI 2021 Towards Face Encryption by Generating Adversarial Identity Masks ICCV 2021 Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving EMNLP 2021 Voice Privacy Through x-Vector and CycleGAN-Based Anonymization Interspeech 2021 ActiveThief: Model Extraction Using Active Learning and Unannotated Public Data AAAI 2020 Adaptive Reward-Poisoning Attacks against Reinforcement Learning ICML 2020 Adversarial Audio: A New Information Hiding Method Interspeech 2020 Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks AAAI 2020 Attention Based Data Hiding with Generative Adversarial Networks AAAI 2020 Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics AAAI 2020 Defending Against Model Stealing Attacks With Adaptive Misinformation CVPR 2020 Differential Privacy for Stackelberg Games IJCAI 2020 ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition CVPR 2020 Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks CVPR 2020 FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions CVPR 2020 Introducing the VoicePrivacy Initiative Interspeech 2020 Inverting Gradients - How easy is it to break privacy in federated learning? NeurIPS 2020