black-box attack

VCP-Attack: Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large Vision-Language Models CVPR 2026 VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy EACL 2026 When Background Matters: Breaking Medical Vision Language Models by Transferable Attack ACL 2026 Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026 ADBA: Approximation Decision Boundary Approach for Black-Box Adversarial Attacks AAAI 2025 Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models IJCAI 2025 Are Exemplar-Based Class Incremental Learning Models Victim of Black-Box Poison Attacks? WACV 2025 Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models AAAI 2025 Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion AAAI 2025 AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts ICCV 2025 B4: A Black-Box Scrubbing Attack on LLM Watermarks NAACL 2025 Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation EMNLP 2025 BinarySelect to Improve Accessibility of Black-Box Attack Research COLING 2025 Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features ICCV 2025 Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks CVPR 2025 Confidence Elicitation: A New Attack Vector for Large Language Models ICLR 2025 DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization NAACL 2025 Enhancing Adversarial Transferability with Adversarial Weight Tuning AAAI 2025 Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training CVPR 2025 Enhancing Transferability of Audio Adversarial Example for Both Frequency- and Time-domain IJCAI 2025 Exploiting Prompt-induced Confidence for Black-Box Attacks on LLMs EMNLP 2025 From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning CVPR 2025 GSBA^K: top-K Geometric Score-based Black-box Attack ICLR 2025 Highly Imperceptible Black-Box Graph Injection Attacks with Reinforcement Learning AAAI 2025 HUANG: A Robust Diffusion Model-based Targeted Adversarial Attack Against Deep Hashing Retrieval AAAI 2025