Privacy

Multi-Token Completion for Text Anonymization EACL 2026 Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis EACL 2026 NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey EACL 2026 Not All Tokens Are Meant to Be Forgotten AAAI 2026 NRGMark: Localized Watermarking for Energy Transparency in Images WACV 2026 Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models AAAI 2026 On the Misalignment Between Data Learnability and Forgettability in Machine Unlearning AAAI 2026 OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models WACV 2026 Optimisation Problems in Constrained Machine Learning AAAI 2026 Optimization and Robustness-Informed Membership Inference Attacks for LLMs AAAI 2026 OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks AAAI 2026 OursFed: Provable Group Fairness-Aware Federated Learning Against Distrust and Fragility AAAI 2026 PAGE: A Unified Approach for Federated Graph Unlearning AAAI 2026 PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology Recovery AAAI 2026 PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination AAAI 2026 PeriUn: Enhancing Unlearning by Selectively Forgetting Peripheral Samples AAAI 2026 Personal Information Parroting in Language Models EACL 2026 Personalized Image Privacy Advisors via Federated Daisy-Chaining WACV 2026 Perturb Your Data: Paraphrase-Guided Training Data Watermarking AAAI 2026 Plug-and-Play Parameter-Efficient Tuning of Embeddings for Federated Recommendation AAAI 2026 PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure AAAI 2026 Prior Refinement Is Better: Diffusion-Driven Graph Harmonization for Federated Graph Learning AAAI 2026 PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration AAAI 2026 Privacy Auditing of Multi-Domain Graph Pre-Trained Model Under Membership Inference Attacks AAAI 2026