adversarial robustness

DeloopSGNN: Revisiting Spectral GNNs Through the Lens of Spatial Aggregation AAAI 2026 Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference AAAI 2026 Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection AAAI 2026 Dynamic Token Reweighting for Robust Vision-Language Models CVPR 2026 EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion AAAI 2026 Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders EACL 2026 Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection ACL 2026 Feature Compression May Be the Root Cause of Adversarial Fragility in Neural Network Classifiers (Student Abstract) AAAI 2026 FRBAT: Conditionally-Visible Physical Backdoor Attack via Fluorescence AAAI 2026 Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models ACL 2026 Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning CVPR 2026 Improving CAPTCHA Robustness via Controlled Image Corruptions (Student Abstract) AAAI 2026 Interpretable and Robust Behavior Abstraction via Environment-Disentangled Heterogeneous Graph AAAI 2026 Jailbreaking Multimodal Large Language Models using Multi-Clip Video ACL 2026 Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation AAAI 2026 Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection AAAI 2026 MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization AAAI 2026 Multi-granularity Intent Modeling with Adversarial Robustness for Sequential Recommendation AAAI 2026 Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models EACL 2026 On Robustness of Linear Classifiers to Targeted Data Poisoning AAAI 2026 PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention CVPR 2026 PEAR: Planner-Executor Agent Robustness Benchmark EACL 2026 PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models CVPR 2026 Reducing the Scope of Language Models AAAI 2026 ReMedQA: Are We Done With Medical Multiple-Choice Benchmarks? EACL 2026