Adversarial Learning

PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 Precision vs. Perturbation: Robustness Analysis of Synonym Attacks in Ukrainian NLP ACL 2025 Pre-Trained Multiple Latent Variable Generative Models are Good Defenders Against Adversarial Attacks WACV 2025 Preventing Latent Diffusion Model-Based Image Mimicry via Angle Shifting and Ensemble Learning IJCAI 2025 Privacy-centric Deep Motion Retargeting for Anonymization of Skeleton-Based Motion Visualization ICCV 2025 Probably Approximately Global Robustness Certification ICML 2025 Problem-dependent Regret for Lexicographic Multi-Armed Bandits with Adversarial Corruptions IJCAI 2025 Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025 ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector CVPR 2025 Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound Images CVPR 2025 Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion ICCV 2025 PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks AAAI 2025 Protecting against simultaneous data poisoning attacks ICLR 2025 Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations CVPR 2025 Prototype Guided Backdoor Defense via Activation Space Manipulation ICCV 2025 PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection CVPR 2025 QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models NAACL 2025 Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation NAACL 2025 Quadratic Upper Bound for Boosting Robustness ICML 2025 QuantAttack: Exploiting Quantization Techniques to Attack Vision Transformers WACV 2025 Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes AAAI 2025 Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective IJCAI 2025 Query-efficient Attack for Black-box Image Inpainting Forensics via Reinforcement Learning AAAI 2025 Quickest Detection of Adversarial Attacks Against Correlated Equilibria AAAI 2025 RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection CVPR 2025