Adversarial Learning

Sample Compression Scheme Reductions ALT 2025 SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP ICLR 2025 Sanitizing Backdoored Graph Neural Networks: A Multidimensional Approach IJCAI 2025 Scaling and Taming Adversarial Training with Synthetic Data ICCV 2025 Scaling Trends in Language Model Robustness ICML 2025 Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 Science-T2I: Addressing Scientific Illusions in Image Synthesis CVPR 2025 Seal Your Backdoor with Variational Defense ICCV 2025 SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models AAAI 2025 Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks CVPR 2025 Selective Unlearning via Representation Erasure Using Domain Adversarial Training ICLR 2025 Self-Improving Robust Preference Optimization ICLR 2025 Severing Spurious Correlations with Data Pruning ICLR 2025 Shadow-Activated Backdoor Attacks on Multimodal Large Language Models ACL 2025 Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025 Sibai: A Few-Shot Meta-Classifier for Poisoning Detection in Federated Learning ICCV 2025 Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation CVPR 2025 Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models CVPR 2025 SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs COLING 2025 Sim4Rec: Data-Free Model Extraction Attack on Sequential Recommendation AAAI 2025 Simplifying Adversarially Robust PAC Learning With Tolerance COLT 2025 SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection ACL 2025 Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems IJCAI 2025 SLADE: Shielding against Dual Exploits in Large Vision-Language Models CVPR 2025 SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation NAACL 2025