Adversarial Learning

Diff-NAT: Better Naturalistic and Aggressive Adversarial Attacks via Class-Optimized Diffusion for Object Detection AAAI 2026 DIMM: Decoupled Multi-hierarchy Kalman Filter via Reinforcement Learning AAAI 2026 Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026 Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference AAAI 2026 DRFGD: Disentangled Representation-Focused Generative Defense for Attack-Tolerant Cross-Modal Hashing AAAI 2026 Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection AAAI 2026 Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping AAAI 2026 Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning AAAI 2026 Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks ACL 2026 Exploiting Missing Data Remediation Strategies Using Adversarial Missingness Attacks AAAI 2026 Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs AAAI 2026 Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System AAAI 2026 Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems AAAI 2026 False Positives Matter: Multidimensional Localization Evaluation and Training-Free Explainable Adversarial Patch Defense AAAI 2026 Feature Compression May Be the Root Cause of Adversarial Fragility in Neural Network Classifiers (Student Abstract) AAAI 2026 FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training AAAI 2026 FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models CVPR 2026 Fractured Glass, Failing Cameras: Simulating Physics-Based Adversarial Samples for Autonomous Driving Systems AAAI 2026 Fragile by Design: On the Limits of Adversarial Defenses in Personalized DreamBooth Generation AAAI 2026 FRBAT: Conditionally-Visible Physical Backdoor Attack via Fluorescence AAAI 2026 From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge AAAI 2026 Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation AAAI 2026 GraphTextack: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs AAAI 2026 Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance AAAI 2026 Hacking Neural Evaluation Metrics with Single Hub Text EACL 2026