privacy-preserving machine learning

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation EMNLP 2024 Generalizing Clinical De-identification Models by Privacy-safe Data Augmentation using GPT-4 EMNLP 2024 Generation and Evaluation of Synthetic Endoscopy Free-Text Reports with Differential Privacy ACL 2024 In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification CVPR 2024 I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data AAAI 2024 Locally Differentially Private In-Context Learning COLING 2024 Online Sensitivity Optimization in Differentially Private Learning AAAI 2024 On the Ability of Developers' Training Data Preservation of Learnware NeurIPS 2024 Practical Privacy-Preserving MLaaS: When Compressive Sensing Meets Generative Networks AAAI 2024 Private prediction for large-scale synthetic text generation EMNLP 2024 Revisiting Differentially Private ReLU Regression NeurIPS 2024 Seesaw: Compensating for Nonlinear Reduction with Linear Computations for Private Inference ICML 2024 SentinelLMs: Encrypted Input Adaptation and Fine-Tuning of Language Models for Private and Secure Inference AAAI 2024 The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers (Student Abstract) AAAI 2024 Trap-MID: Trapdoor-based Defense against Model Inversion Attacks NeurIPS 2024 Ungeneralizable Examples CVPR 2024 k-Means Clustering with Distance-Based Privacy NeurIPS 2023 A Privacy-Friendly Approach to Data Valuation NeurIPS 2023 A Randomized Approach to Tight Privacy Accounting NeurIPS 2023 A Survey of Federated Evaluation in Federated Learning IJCAI 2023 Bounding training data reconstruction in DP-SGD NeurIPS 2023 Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis ICML 2023 Cookie Consent Has Disparate Impact on Estimation Accuracy NeurIPS 2023 Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards ICML 2023 Dropout Is NOT All You Need to Prevent Gradient Leakage AAAI 2023