Adversarial Learning

Good Can Sometimes be Bad: A Unified Attack against 3D Point Cloud Classifier by a Flexible Isotropic Resampling CVPR 2026 Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models UAI 2026 HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human–LLM Collaborative Writing ACL 2026 HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment ACL 2026 Hidden Dangers of Compositional Generation: Diagnosing Semantic Safety Failures in Text-to-Image Models CVPR 2026 Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning CVPR 2026 Improving Adversarial Transferability with Local Perturbation Augmentation CVPR 2026 In-Context Representation Hijacking ACL 2026 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 IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness CVPR 2026 Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection CVPR 2026 Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models ACL 2026 JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization CVPR 2026 LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents CVPR 2026 Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception CVPR 2026 Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain ACL 2026 Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection ACL 2026 Locket: Robust Feature-Locking Technique for Language Models ACL 2026 LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation ACL 2026 MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning ACL 2026 Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026 Mitigating Error Amplification in Fast Adversarial Training CVPR 2026 MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks ACL 2026 Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints CVPR 2026