Privacy

AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO EMNLP 2025 ALGEN: Few-shot Inversion Attacks on Textual Embeddings via Cross-Model Alignment and Generation ACL 2025 A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality EMNLP 2025 A New Federated Learning Framework Against Gradient Inversion Attacks AAAI 2025 AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy WACV 2025 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 Anti-Tamper Protection for Unauthorized Individual Image Generation ICCV 2025 A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks AAAI 2025 Assessing the Exposure to Public Knowledge in Policy-Protected Description Logic Ontologies IJCAI 2025 A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models ACL 2025 Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images! ICCV 2025 Attribute Inference Attacks for Federated Regression Tasks AAAI 2025 Augmented Adversarial Trigger Learning NAACL 2025 Automated Detection of Pre-training Text in Black-box LLMs IJCAI 2025 Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025 A Watermark for Auto-Regressive Speech Generation Models Interspeech 2025 Backdoor Attack on Vertical Federated Graph Neural Network Learning IJCAI 2025 Backdoor Attacks Against No-Reference Image Quality Assessment Models via a Scalable Trigger AAAI 2025 Backdoor Defense via Enhanced Splitting and Trap Isolation ICCV 2025 Backdooring Self-Supervised Contrastive Learning by Noisy Alignment ICCV 2025 Backdoor Mitigation by Distance-Driven Detoxification ICCV 2025 Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models AAAI 2025 BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models CVPR 2025 Balancing Privacy and Performance: A Many-in-One Approach for Image Anonymization AAAI 2025 Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts NAACL 2025