Security

Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection CVPR 2026 Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation ACL 2026 Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection ACL 2026 Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models CVPR 2026 BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation CVPR 2026 BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks ACL 2026 CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing ACL 2026 CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems ACL 2026 ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering CVPR 2026 CodeRipple: Wavelet-Based Detection of LLM-Generated Code ACL 2026 CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training ACL 2026 Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors ACL 2026 Conjunctive Prompt Attacks in Multi-Agent LLM Systems ACL 2026 COPYLENS: Towards Copyrighted Characters Infringement Detection via Copyright-Aware Prompt Learning CVPR 2026 Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks ACL 2026 CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models CVPR 2026 CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning ACL 2026 Decoupling Defense Strategies for Robust Image Watermarking CVPR 2026 DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation ACL 2026 DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion CVPR 2026 Defending against Traffic Analysis Attacks with Flexible In-Network Obfuscation NSDI 2026 Defending Unauthorized Model Merging via Dual-Stage Weight Protection CVPR 2026 Defense Against Knowledge Poisoning Attack on GraphRAG ACL 2026 Defenses Against Prompt Attacks Learn Surface Heuristics ACL 2026 Detect Any AI-Counterfeited Text Image CVPR 2026