Adversarial Learning

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026 CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions ACL 2026 Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation ACL 2026 Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors ACL 2026 Conjunctive Prompt Attacks in Multi-Agent LLM Systems ACL 2026 Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models ACL 2026 CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks ACL 2026 Cross-Subject EEG-to-Video Reconstruction and Beyond CVPR 2026 DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples CVPR 2026 Decoupling Defense Strategies for Robust Image Watermarking CVPR 2026 DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion CVPR 2026 Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring ACL 2026 DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs ACL 2026 DualMirage: Hunting Stealthy Multimodal LLM Agents via CAPTCHAs with Contour and Adversarial Illusions CVPR 2026 Dynamic Token Reweighting for Robust Vision-Language Models CVPR 2026 Echoes of Ownership: Adversarial-Guided Dual Injection for Copyright Protection in MLLMs CVPR 2026 Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance ACL 2026 Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures CVPR 2026 FeatureFool: Zero-Query Fooling of Video Models via Feature Map CVPR 2026 Fingerprinting LLMs via Prompt Injection ACL 2026 FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction CVPR 2026 Forensic-Friendly Image Manipulation via Controllable Latent Diffusion CVPR 2026 Fractal Camouflage: A Bio-Inspired Approach for Multi-Scale Adversarial Attacks in the Infrared Domain CVPR 2026 GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models CVPR 2026 Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting CVPR 2026