Privacy

Voice Guard: Protecting Voice Privacy with Strong and Imperceptible Adversarial Perturbation in the Time Domain IJCAI 2023 Watermarking LLMs with Weight Quantization EMNLP 2023 Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes ICML 2023 What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks ICCV 2023 What Can We Learn from Unlearnable Datasets? NeurIPS 2023 What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners? NeurIPS 2023 Why Is Public Pretraining Necessary for Private Model Training? ICML 2023 Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation AAAI 2023 zPROBE: Zero Peek Robustness Checks for Federated Learning ICCV 2023 AB/BA analysis: A framework for estimating keyword spotting recall improvement while maintaining audio privacy NAACL 2022 A bounded-noise mechanism for differential privacy COLT 2022 Acceleration of Federated Learning with Alleviated Forgetting in Local Training ICLR 2022 ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection NeurIPS 2022 A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning NeurIPS 2022 Adaptive Differential Privacy for Language Model Training ACL 2022 Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE AISTATS 2022 Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation ACL 2022 A Differentially Private Linear-Time fPTAS for the Minimum Enclosing Ball Problem NeurIPS 2022 Admissible Policy Teaching through Reward Design AAAI 2022 Adversarial Authorship Attribution for Deobfuscation ACL 2022 A Federated Approach to Predicting Emojis in Hindi Tweets EMNLP 2022 A Fusion-Denoising Attack on InstaHide with Data Augmentation AAAI 2022 A General Framework for Auditing Differentially Private Machine Learning NeurIPS 2022 A Joint Exponential Mechanism For Differentially Private Top-k ICML 2022 Algorithms that Approximate Data Removal: New Results and Limitations NeurIPS 2022