Privacy

DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection AAAI 2022 Encrypted Linear Contextual Bandit AISTATS 2022 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 Fair NLP Models with Differentially Private Text Encoders EMNLP 2022 Federated Learning with Noisy User Feedback NAACL 2022 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022 GradViT: Gradient Inversion of Vision Transformers CVPR 2022 How Private Is Your RL Policy? An Inverse RL Based Analysis Framework AAAI 2022 Hyperparameter Tuning with Renyi Differential Privacy ICLR 2022 Improved Utility Analysis of Private CountSketch NeurIPS 2022 Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022 Just Fine-tune Twice: Selective Differential Privacy for Large Language Models EMNLP 2022 Knowledge Removal in Sampling-based Bayesian Inference ICLR 2022 Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract) IJCAI 2022 Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes ACML 2022 Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions ICML 2022 MetaFinger: Fingerprinting the Deep Neural Networks with Meta-training IJCAI 2022 MExMI: Pool-based Active Model Extraction Crossover Membership Inference NeurIPS 2022 MockingBERT: A Method for Retroactively Adding Resilience to NLP Models COLING 2022 Model Stealing Defense against Exploiting Information Leak through the Interpretation of Deep Neural Nets IJCAI 2022 Network change point localisation under local differential privacy NeurIPS 2022 Neural Text Sanitization with Explicit Measures of Privacy Risk AACL 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022 Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022