Privacy

PROMPRINT: Prompt Fingerprinting via First-Token Response for LLM App Cloning Detection ACL 2026 Protecting Bystander Privacy via Selective Hearing in Audio LLMs ACL 2026 ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning CVPR 2026 Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms ACL 2026 Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization CVPR 2026 SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains CVPR 2026 SANER: Switchable Adapter with Non-parametric Enhanced Routing for Person De-Reidentification CVPR 2026 SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning WACV 2026 SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute AAAI 2026 Selective Span-Level Unlearning for Large Language Models ACL 2026 SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models ACL 2026 Stake the Points: Structure-Faithful Instance Unlearning CVPR 2026 Stealing Split Learning Bottom Models by Recovering Embedding Geometry CVPR 2026 Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems CVPR 2026 Towards Cross-Modal Preservation, Consistency and Alignment for Privacy-Preserving Visible-Infrared Person Re-Identification CVPR 2026 Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation ACL 2026 Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models CVPR 2026 Unsafe2Safe: Controllable Image Anonymization for Downstream Utility CVPR 2026 User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios ACL 2026 When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing AAAI 2026 Whispering Agents: A Event-Driven Covert Communication Protocol for the Internet of Agents AAAI 2026 Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models ACL 2026 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning ACL 2025 ACE: Anti-Editing Concept Erasure in Text-to-Image Models CVPR 2025 Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning. ICCV 2025