Adversarial Learning

TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models CVPR 2026 Towards Human-Imperceptible Backdoor Attacks on Text-to-Image Diffusion Models CVPR 2026 Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks CVPR 2026 Towards Robust Multimodal Large Language Models Against Jailbreak Attacks CVPR 2026 Transform to Transfer: Boosting Adversarial Attack Transferability on Vision-Language Pre-training Models CVPR 2026 TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration CVPR 2026 TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models CVPR 2026 UniDef: Universal Defense Against Unauthorized Image Manipulation CVPR 2026 UniGame: Turning a Unified Multimodal Model Into Its Own Adversary CVPR 2026 Unleashing Stealthy Backdoor Pandemic by Infecting a Single Diffusion Model CVPR 2026 Unnoticed Yet Effective: A Hybrid Physical Camouflage Framework Against DNNs and Human Perception AAAI 2026 VCP-Attack: Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large Vision-Language Models CVPR 2026 Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning ACL 2026 What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs CVPR 2026 When Background Matters: Breaking Medical Vision Language Models by Transferable Attack ACL 2026 When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness CVPR 2026 When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents ACL 2026 When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models CVPR 2026 XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants ACL 2026 $δ$-STEAL: LLM Stealing Attack with Local Differential Privacy ACML 2025 3SAT: A Simple Self-Supervised Adversarial Training Framework AAAI 2025 A²RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion AAAI 2025 Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model ACML 2025 Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents NAACL 2025 ADBA: Approximation Decision Boundary Approach for Black-Box Adversarial Attacks AAAI 2025