Adversarial Learning

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025 Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization CVPR 2025 HeTa: Relation-wise Heterogeneous Graph Foundation Attack Model IJCAI 2025 Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models ICCV 2025 HoneypotNet: Backdoor Attacks Against Model Extraction AAAI 2025 I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models CVPR 2025 IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization ICCV 2025 IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves ICCV 2025 Identifying and Mitigating Spurious Correlation in Multi-Task Learning CVPR 2025 IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation CVPR 2025 Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement CVPR 2025 Improving Adversarial Transferability via Decision Boundary Adaptation UAI 2025 Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization AAAI 2025 Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation CVPR 2025 Improving Transferable Targeted Attacks with Feature Tuning Mixup CVPR 2025 InfAL: Inference Time Adversarial Learning for Improving Research Ideation EMNLP 2025 Instant Adversarial Purification with Adversarial Consistency Distillation CVPR 2025 Integrating Argumentation Features for Enhanced Propaganda Detection in Arabic Narratives on the Israeli War on Gaza COLING 2025 Invisible Backdoor Attack against Self-supervised Learning CVPR 2025 Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness NAACL 2025 Jailbreak Attack Initializations as Extractors of Compliance Directions EMNLP 2025 Jailbreaking? One Step Is Enough! ACL 2025 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025 KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models AAAI 2025