Security

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game ACL 2026 Don’t Corrupt the Fact: A Trustworthy RAG Watermarking Framework based on Dual Factual Shield ACL 2026 Efficient Provably Secure Linguistic Steganography via Range Coding ACL 2026 Eliminate Distance Differences Induced by Backdoor Attacks: Layer-Selective Training and Clipping to Mask Backdoor Models CVPR 2026 Enhancing the Security of Visual Speaker Authentication Based on Dynamic Lip-Print Analysis CVPR 2026 Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS ACL 2026 Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures CVPR 2026 False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models ACL 2026 Fast-MIA: Efficient and Scalable Membership Inference for LLMs ACL 2026 FeatureFool: Zero-Query Fooling of Video Models via Feature Map CVPR 2026 Fingerprinting LLMs via Prompt Injection ACL 2026 FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction CVPR 2026 Frankentext: Stitching random text fragments into long-form narratives ACL 2026 From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing CVPR 2026 From TDMA to CDMA: A Multi-bit Watermark for Diffusion Language Models ACL 2026 From Trust to Compromise: Outcome-Verified LLM Phishing Simulation and Real-Time Defense ACL 2026 GEM-TFL: Bridging Weak and Full Supervision for Forgery Localization through EM-Guided Decomposition and Temporal Refinement CVPR 2026 Good Can Sometimes be Bad: A Unified Attack against 3D Point Cloud Classifier by a Flexible Isotropic Resampling CVPR 2026 GROW: Watermark Generation with Progressive Guidance for Diffusion Models CVPR 2026 Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models UAI 2026 GVIS: Generative Vector Image Steganography CVPR 2026 Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning CVPR 2026 IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding CVPR 2026 ImF: Embedding an Implicit Fingerprint in Your Large Language Models ACL 2026 Inconsistency-aware Multimodal Schrodinger Bridge for Deepfake Localization CVPR 2026