Research map / Adversarial robustness and security / Attacks on text and graphs
VCP-Attack: Visual-Contrastive Projection for Transferable Black-Box Targeted Attacks on Large Vision-Language Models
Jiawei Zhao, Minjie Du, Zihan Qin, Zhuoran Wang, Lizhe Xie, Yining Hu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add PCA subspace projection (d = 10) (ablation) | VCP-Attack · Open-source LVLMs avg | ASR (%): 90.5 -> 96.7 | Improved |
| use PCA dimension 10 instead of 5, 30 or 50 (ablation) | VCP-Attack · Open-source LVLMs avg | ASR (%) | Improved |
| set positive loss coefficient alpha = 0.8 mixing top-k and max terms (ablation) | VCP-Attack · Open-source LVLMs avg | ASR (%) | Improved |
| use top-k/top-m = (10,10) sampling instead of larger or no filtering (ablation) | VCP-Attack · Open-source LVLMs avg | ASR (%) | Improved |
| increase perturbation budget from 8/255 to 32/255 (ablation) | VCP-Attack · Open-source LVLMs avg | ASR (%): up to 98.2 | Improved |
| VCP-Attack vs strongest baseline (M-Attack) | VCP-Attack · Open-source LVLMs avg | ASR (%): 71.8 -> 94.2 | Improved |
| VCP-Attack vs strongest baseline on Claude-3.7-Sonnet | VCP-Attack · Claude-3.7-Sonnet | ASR (%): 38.8 -> 61.1 | Improved |
| scale victim model size from 14B to 38B/78B | M-Attack and FOA-Attack · InternVL3 | ASR (%): 87.7 -> 54.4 (M-Attack) | Hurt |
Closest papers by meaning
- A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1 (NeurIPS 2025 · similarity 0.91)
- Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction (CVPR 2026 · similarity 0.91)
- Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks (CVPR 2025 · similarity 0.89)
- Attention! Your Vision Language Model Could Be Maliciously Manipulated (NeurIPS 2025 · similarity 0.89)
- Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models (NeurIPS 2026 · similarity 0.88)
- Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
