adversarial perturbation

Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models ACL 2026 Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection ACL 2026 TarPro: Targeted Protection Against Malicious Image Editing AAAI 2026 The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces ACL 2026 Thesis Proposal: Comparing Human and Model Perception of Writing Style under Controlled Perturbations EACL 2026 Time Shuffle: A Transferability-Booster for Multiple Audio Adversarial Tasks AAAI 2026 Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction CVPR 2026 Towards Robust Multimodal Large Language Models Against Jailbreak Attacks CVPR 2026 Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026 UniDef: Universal Defense Against Unauthorized Image Manipulation CVPR 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 A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment CVPR 2025 A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection AAAI 2025 Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approach AAAI 2025 Adversarial Attention Perturbations for Large Object Detection Transformers ICCV 2025 Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI ICLR 2025 Adversarial Perturbations Improve Generalization of Confidence Prediction in Medical Image Segmentation MIDL 2025 Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training EMNLP 2025 AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective IJCAI 2025 AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption ICLR 2025 Algorithmic Stability Based Generalization Bounds for Adversarial Training ICLR 2025 AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025 Are Multimodal LLMs Robust Against Adversarial Perturbations? RoMMath: A Systematic Evaluation on Multimodal Math Reasoning NAACL 2025 A Transfer Attack to Image Watermarks ICLR 2025