Adversarial Learning

AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025 A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos ACL 2025 An Engorgio Prompt Makes Large Language Model Babble on ICLR 2025 A New Adversarial Perspective for LiDAR-based 3D Object Detection AAAI 2025 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models CVPR 2025 Atoxia: Red-teaming Large Language Models with Target Toxic Answers NAACL 2025 Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models EMNLP 2025 Attacking Vision-Language Computer Agents via Pop-ups ACL 2025 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Attention-Imperceptible Backdoor Attacks on Vision Transformers AAAI 2025 Augmented Adversarial Trigger Learning NAACL 2025 A Unified, Resilient, and Explainable Adversarial Patch Detector CVPR 2025 AUTE: Peer-Alignment and Self-Unlearning Boost Adversarial Robustness for Training Ensemble Models AAAI 2025 AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025 Backdoor Attack on Propagation-based Rumor Detectors AAAI 2025 Backdoor Attacks on Neural Networks via One-Bit Flip ICCV 2025 Backdoor Defense via Enhanced Splitting and Trap Isolation ICCV 2025 Backdooring Self-Supervised Contrastive Learning by Noisy Alignment ICCV 2025 BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models CVPR 2025 Beneath the Facade: Probing Safety Vulnerabilities in LLMs via Auto-Generated Jailbreak Prompts EMNLP 2025 Bias in the Mirror : Are LLMs opinions robust to their own adversarial attacks ACL 2025 BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks NAACL 2025 Bit-Flip Induced Latency Attacks in Object Detection WACV 2025 Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models CVPR 2025