Privacy

Influencer Backdoor Attack on Semantic Segmentation ICLR 2024 Instance-Optimal Private Density Estimation in the Wasserstein Distance NeurIPS 2024 Instance-Specific Asymmetric Sensitivity in Differential Privacy NeurIPS 2024 Instance-Wise Laplace Mechanism via Deep Reinforcement Learning (Student Abstract) AAAI 2024 Integer Is Enough: When Vertical Federated Learning Meets Rounding AAAI 2024 Invariant Aggregator for Defending against Federated Backdoor Attacks AISTATS 2024 Invisible Image Watermarks Are Provably Removable Using Generative AI NeurIPS 2024 I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data AAAI 2024 IPRemover: A Generative Model Inversion Attack against Deep Neural Network Fingerprinting and Watermarking AAAI 2024 Is It Safe to Tell Your Story? Towards Achieving Privacy for Sensitive Narratives EMNLP 2024 JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL 2024 Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data AISTATS 2024 Keep it Private: Unsupervised Privatization of Online Text NAACL 2024 Knowledge Distillation in Federated Learning: A Practical Guide IJCAI 2024 KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server EMNLP 2024 Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models ICLR 2024 Label Leakage in Vertical Federated Learning: A Survey IJCAI 2024 Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning NeurIPS 2024 Language Model Inversion ICLR 2024 Large Language Models Can Be Contextual Privacy Protection Learners EMNLP 2024 Large Language Model Unlearning NeurIPS 2024 LatticeGen: Hiding Generated Text in a Lattice for Privacy-Aware Large Language Model Generation on Cloud NAACL 2024 Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation AAAI 2024 Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning CVPR 2024 Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs EACL 2024