black-box attack

Improving Adversarial Transferability via Decision Boundary Adaptation UAI 2025 Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising CVPR 2025 JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025 KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025 Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment AAAI 2025 Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis CVPR 2025 Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries ACL 2025 Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithms EMNLP 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025 PLA: Prompt Learning Attack against Text-to-Image Generative Models ICCV 2025 Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented Learning AAAI 2025 Practicable Black-Box Evasion Attacks on Link Prediction in Dynamic Graphs—a Graph Sequential Embedding Method AAAI 2025 Query-efficient Attack for Black-box Image Inpainting Forensics via Reinforcement Learning AAAI 2025 Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters AAAI 2025 SALSA: A Secure, Adaptive and Label-Agnostic Scalable Algorithm for Machine Unlearning UAI 2025 SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout ICCV 2025 Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025 Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring NAACL 2025 The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems EMNLP 2025 Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance ICCV 2025 Training Robust Ensembles Requires Rethinking Lipschitz Continuity ICLR 2025 Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving CVPR 2024 A General Black-box Adversarial Attack on Graph-based Fake News Detectors IJCAI 2024 Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection NeurIPS 2024 Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models NeurIPS 2024