Privacy

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks AAAI 2024 Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion EMNLP 2024 Teach LLMs to Phish: Stealing Private Information from Language Models ICLR 2024 TEI Specifications for a Sustainable Management of Digitized Holocaust Testimonies COLING 2024 Text Embedding Inversion Security for Multilingual Language Models ACL 2024 Text-Enhanced Data-free Approach for Federated Class-Incremental Learning CVPR 2024 The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) ACL 2024 The Impact of Differential Privacy on Group Disparity Mitigation NAACL 2024 The importance of feature preprocessing for differentially private linear optimization ICLR 2024 The Limits of Differential Privacy in Online Learning NeurIPS 2024 The Relative Gaussian Mechanism and its Application to Private Gradient Descent AISTATS 2024 The Rise of AI-Generated Content in Wikipedia EMNLP 2024 The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly AAAI 2024 Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting EMNLP 2024 Thompson Sampling Itself is Differentially Private AISTATS 2024 To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models EMNLP 2024 To Share or Not to Share: What Risks Would Laypeople Accept to Give Sensitive Data to Differentially-Private NLP Systems? COLING 2024 Toward effective protection against diffusion-based mimicry through score distillation ICLR 2024 Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs ICLR 2024 Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks ICLR 2024 Towards Memorization-Free Diffusion Models CVPR 2024 Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation AAAI 2024 Towards More Realistic Membership Inference Attacks on Large Diffusion Models WACV 2024 Towards Privacy-Aware Sign Language Translation at Scale ACL 2024 Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features ICLR 2024