Privacy

A Content-Preserving Secure Linguistic Steganography AAAI 2026 Breaking Cross-View Associations: Byzantine Model Poisoning Attack against Vertical Federated Learning AAAI 2026 Bridging Privacy and Provenance: Traceable Virtual Identity Generation CVPR 2026 CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems ACL 2026 CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents ACL 2026 CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training ACL 2026 ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance ACL 2026 CRIME: Community Rewiring for Influence and Masking Entities in Social Networks (Student Abstract) AAAI 2026 De-Anonymization at Scale via Tournament-Style Attribution ACL 2026 Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference ACL 2026 Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models EACL 2026 Defending against Traffic Analysis Attacks with Flexible In-Network Obfuscation NSDI 2026 Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game ACL 2026 Differentially Private 2D Human Pose Estimation CVPR 2026 Differentially Private Language Generation and Identification in the Limit (Extended Abstract) COLT 2026 Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework ACL 2026 Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models ACL 2026 Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning ACL 2026 Exploring Cross-Lingual Voice Conversion Methods for Anonymizing Low-Resource Text-to-Speech EACL 2026 Fast-MIA: Efficient and Scalable Membership Inference for LLMs ACL 2026 FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training AAAI 2026 FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data ACL 2026 FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning CVPR 2026 Frequency-domain Manipulation for Face Obfuscation CVPR 2026 From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal CVPR 2026