Privacy

Fully Decentralized Certified Unlearning CVPR 2026 Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data ACL 2026 GDFA: Geometry-Driven Federated Unlearning with Directional Task Vector Alignment CVPR 2026 Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations CVPR 2026 Grokked Models are Better Unlearners UAI 2026 ImF: Embedding an Implicit Fingerprint in Your Large Language Models ACL 2026 Imprint of the Forgotten: Stealthy Membership Inference in Unlearned Graph Neural Networks AAAI 2026 IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness CVPR 2026 iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification AAAI 2026 Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation ACL 2026 Latent Diffusion Inversion Requires Understanding the Latent Space CVPR 2026 LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators AAAI 2026 LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport ACL 2026 Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning ACL 2026 No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants ACL 2026 No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation CVPR 2026 Osprey: Transparent and Efficient Virtual Memory for Secure Computation OSDI 2026 Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing ACL 2026 pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning CVPR 2026 PII-Bench: Evaluating Query-Aware Privacy Protection Systems ACL 2026 PlanetServe: A Decentralized, Scalable, and Privacy-Preserving Overlay for Democratizing Large Language Model Serving NSDI 2026 Powerful Training-Free Membership Inference Against Fine-Tuned Autoregressive Language Models ACL 2026 PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation ACL 2026 Privacy-preserving Prosody Representation Learning ACL 2026 PrivateEyes: Gaze-Preserving Anonymization for Data Sharing CVPR 2026