Adversarial Learning

RemedyGS: Defend 3D Gaussian Splatting Against Computation Cost Attacks CVPR 2026 ReMoE: Region-Mixture Experts for Adversarially-Robust Vision Transformers CVPR 2026 RevINN: An End-to-End Invertible Neural Network for Reversible Adversarial Examples Generation CVPR 2026 Robust Membership Inference for Large Language Models under Adversarial Generative Corruption ACL 2026 ROSE: An Intent-Centered Evaluation Metric for NL2SQL ACL 2026 Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization ACL 2026 RunawayEvil: Jailbreaking the Image-to-Video Generative Models CVPR 2026 SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors CVPR 2026 SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning CVPR 2026 Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments ACL 2026 Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking ACL 2026 SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking ACL 2026 Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack CVPR 2026 SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models ACL 2026 SpyComet at SemEval-2026 Task 11: When Adversarial Debiasing Backfires - A Comparison of Data-Level and Model-Level Debiasing SemEval 2026 StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation ACL 2026 Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models ACL 2026 TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems ACL 2026 Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation CVPR 2026 Test-Time Attention Purification for Backdoored Large Vision Language Models CVPR 2026 The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models CVPR 2026 The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation CVPR 2026 The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers CVPR 2026 Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems CVPR 2026 The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces ACL 2026