adversarial attack

Mind the Gap: A Practical Attack on GGUF Quantization ICML 2025 Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis CVPR 2025 Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking CVPR 2025 MiniMal: Hard-Label Adversarial Attack Against Static Malware Detection with Minimal Perturbation IJCAI 2025 Minimizing Queries, Maximizing Impact: Adaptive Score-Based Attack and Defense for Sentiment Analysis IJCNLP 2025 Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion EMNLP 2025 Model Poisoning Attacks to Federated Learning via Multi-Round Consistency CVPR 2025 Monte Carlo Tree Search Based Prompt Autogeneration for Jailbreak Attacks against LLMs COLING 2025 MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework CVPR 2025 MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming ACL 2025 Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment ICML 2025 Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries ACL 2025 MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 Neuromanifold-Regularized KANs for Shape-fair Feature Representations ICCV 2025 NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025 NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary CVPR 2025 No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks ICML 2025 Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025 Nullspace Disentanglement for Red Teaming Language Models EMNLP 2025 NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors AAAI 2025 Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition ICML 2025 One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models ICCV 2025 One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models ICCV 2025 One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems EMNLP 2025 On Guardrail Models’ Robustness to Mutations and Adversarial Attacks EMNLP 2025