Adversarial Learning

Speaker Normalization and Content Restoration for Zero-Shot Voice Conversion with Attention-Enhanced Discriminator Interspeech 2025 SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods ACL 2025 SQL Injection Jailbreak: A Structural Disaster of Large Language Models ACL 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors ACL 2025 sudo rm -rf agentic_security ACL 2025 SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learning AAAI 2025 TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models CVPR 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025 Too Helpful, Too Harmless, Too Honest or Just Right? EMNLP 2025 Towards Adversarially Robust Dataset Distillation by Curvature Regularization AAAI 2025 Towards Better Robustness Against Natural Corruptions in Document Tampering Localization AAAI 2025 Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks CVPR 2025 Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification JMLR 2025 Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification ICCV 2025 Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models AAAI 2025 TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs AAAI 2025 Transferable Adversarial Face Attack with Text Controlled Attribute AAAI 2025 Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025 Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization JMLR 2025 Understanding Model Ensemble in Transferable Adversarial Attack ICML 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors AAAI 2025