Security

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models ACL 2026 Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries ACL 2026 Investigating Self-Supervised Representations for Audio-Visual Deepfake Detection CVPR 2026 IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness CVPR 2026 JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents ACL 2026 Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation ACL 2026 LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents CVPR 2026 Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection ACL 2026 LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation ACL 2026 Logit-Margin Repulsion for Backdoor Defense CVPR 2026 Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage ACL 2026 Mark4D: Temporally-Consistent Watermarking for 4D Gaussian Splatting CVPR 2026 MaxMark: High-Capacity Diffusion-Native Watermarking via Robust and Invertible Latent Embedding CVPR 2026 Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models ACL 2026 Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking CVPR 2026 MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning ACL 2026 Modeling Human Adversarial Strategy Adaptation in Multi-Turn Language Model Interactions CoNLL 2026 Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models CVPR 2026 NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models ACL 2026 No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants ACL 2026 NOWA: Null-space Optical Watermark for Invisible Capture Fingerprinting and Tamper Localization CVPR 2026 On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference ACL 2026 Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services ACL 2026 Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation CVPR 2026 PARASITE: Conditional System Prompt Poisoning to Hijack LLMs ACL 2026