Adversarial Learning

SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout ICCV 2025 Speed Master: Quick or Slow Play to Attack Speaker Recognition AAAI 2025 SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025 SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution ICML 2025 Stable Fair Graph Representation Learning with Lipschitz Constraint ICML 2025 Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025 StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions ICCV 2025 Stealthy Backdoor Attack in Federated Learning via Adaptive Layer-wise Gradient Alignment ICCV 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models CVPR 2025 Stochastic Bandits Robust to Adversarial Attacks ICLR 2025 Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent CVPR 2025 Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors ACL 2025 Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection ACL 2025 Style Transfer with Multi-iteration Preference Optimization NAACL 2025 Sugar-Coated Poison: Benign Generation Unlocks Jailbreaking EMNLP 2025 SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learning AAAI 2025 SyncGaussian: Stable 3D Gaussian-Based Talking Head Generation with Enhanced Lip Sync via Discriminative Speech Features IJCAI 2025 Synonym-unaware Fast Adversarial Training against Textual Adversarial Attacks NAACL 2025 Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability ICML 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 TaeBench: Improving Quality of Toxic Adversarial Examples NAACL 2025 TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models CVPR 2025 Targeted Attack Improves Protection against Unauthorized Diffusion Customization ICLR 2025 TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification CVPR 2025