Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

Xiang Fang, Wanlong Fang, Changshuo WangAAAI 2026 · DOI

BibTeX
@inproceedings{fang2026unveiling,
  author = {Xiang Fang and Wanlong Fang and Changshuo Wang},
  title = {{Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2026},
  doi = {10.1609/aaai.v40i5.37388},
}

Loading related content...

Figure