Adversarial Learning

ToxiPrompt: A Two-Stage Red-Teaming Approach for Balancing Adversarial Prompt Diversity and Response Toxicity EACL 2026 TRACE: Confounder-free Adversarial Fine-tuning for Robust Object Detection WACV 2026 Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach AAAI 2026 Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026 Transferable Hypergraph Attack via Injecting Nodes into Pivotal Hyperedges AAAI 2026 Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks Using Hyperparameter Tuning AAAI 2026 TVChain: Leveraging Textual-Visual Prompt Chains for Jailbreaking Large Vision-Language Models AAAI 2026 UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks WACV 2026 Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics AAAI 2026 Uncovering and Mitigating Transient Blindness in Multimodal Model Editing AAAI 2026 Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion AAAI 2026 Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models EACL 2026 Unnoticed Yet Effective: A Hybrid Physical Camouflage Framework Against DNNs and Human Perception AAAI 2026 Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization AAAI 2026 VBF++: Variational Bayesian Fusion with Context-Aware Priors and Recommendation-Guided Adversarial Refinement for Multimodal Video Recommendation AAAI 2026 Visual-Friendly Concept Protection via Selective Adversarial Perturbations AAAI 2026 VoiceCloak: A Multi-Dimensional Defense Framework Against Unauthorized Diffusion-Based Voice Cloning AAAI 2026 Vulnerability-Aware Robust Multimodal Adversarial Training AAAI 2026 σ-zero: Gradient-based Optimization of ℓ_0-norm Adversarial Examples ICLR 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 A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment CVPR 2025 AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation AAAI 2025 A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection AAAI 2025 ACAttack: Adaptive Cross Attacking RGB-T Tracker via Multi-Modal Response Decoupling CVPR 2025