Privacy

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) ACL 2024 The Limits of Differential Privacy in Online Learning NeurIPS 2024 Towards More Realistic Membership Inference Attacks on Large Diffusion Models WACV 2024 TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution AAAI 2024 Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries ACL 2024 Trap-MID: Trapdoor-based Defense against Model Inversion Attacks NeurIPS 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NeurIPS 2024 Universal Exact Compression of Differentially Private Mechanisms NeurIPS 2024 Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning EMNLP 2024 Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NeurIPS 2024 VoiceDefense: Protecting Automatic Speaker Verification Models Against Black-box Adversarial Attacks Interspeech 2024 WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks NeurIPS 2024 When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search NeurIPS 2024 Active Membership Inference Attack under Local Differential Privacy in Federated Learning AISTATS 2023 A Customized Text Sanitization Mechanism with Differential Privacy ACL 2023 Addax: A fast, private, and accountable ad exchange infrastructure NSDI 2023 Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks EMNLP 2023 Attention-Enhancing Backdoor Attacks Against BERT-based Models EMNLP 2023 Automated De-Identification of Arabic Medical Records EMNLP 2023 Bayesian Estimation of Differential Privacy ICML 2023 Boomerang: Metadata-Private Messaging under Hardware Trust NSDI 2023 Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information NeurIPS 2023 Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries ICLR 2023 CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search CVPR 2023