Privacy

TrustMark: Robust Watermarking and Watermark Removal for Arbitrary Resolution Images ICCV 2025 TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025 Universal Backdoor Defense via Label Consistency in Vertical Federated Learning IJCAI 2025 Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems NAACL 2025 Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025 VerA: Versatile Anonymization Applicable to Clinical Facial Photographs WACV 2025 Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025 VLA-Mark: A cross modal watermark for large vision-language alignment models EMNLP 2025 Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety NAACL 2025 VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distribution AAAI 2025 WAKE: Watermarking Audio with Key Enrichment Interspeech 2025 Watermarking Large Language Models: An Unbiased and Low-risk Method ACL 2025 WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks ACL 2025 When and Where do Data Poisons Attack Textual Inversion? ICCV 2025 When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs ACL 2025 Where Does This Data Come From? Enhanced Source Inference Attacks in Federated Learning IJCAI 2025 Who Controls the Authorization? Invertible Networks for Copyright Protection in Text-to-Image Synthesis ICCV 2025 With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting IJCNLP 2025 You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks Interspeech 2025 Zero-shot Federated Unlearning via Transforming from Data-Dependent to Personalized Model-Centric IJCAI 2025 ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models ICCV 2025 A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives AAAI 2024 A Learnable Discrete-Prior Fusion Autoencoder with Contrastive Learning for Tabular Data Synthesis AAAI 2024 An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference EMNLP 2024 Assessing Authenticity and Anonymity of Synthetic User-generated Content in the Medical Domain EACL 2024