conftrace_

utility-privacy tradeoff

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

differential privacy (3) membership inference attack (2) language model (2) privacy regularization (1) token-level optimization (1) privacy setting (1) privacy verification (1) tensor low-rank proximal optimization (1) neural network (1) privacy defense (1)

Papers

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off ICML 2025 Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training ACL 2025 A Randomized Approach to Tight Privacy Accounting NeurIPS 2023 Improving Robustness to Model Inversion Attacks via Mutual Information Regularization AAAI 2021 Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels NAACL 2021 When Does Data Augmentation Help With Membership Inference Attacks? ICML 2021