Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models

Feb-14-2026, 17:21:56 GMT–Neural Information Processing Systems

Large Vision-Language Models (L VLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding tasks.

arxiv preprint arxiv, large language model, machine learning, (17 more...)

Neural Information Processing Systems

Feb-14-2026, 17:21:56 GMT

Conferences PDF

Country:
- Asia
  - China > Guangdong Province
    - Guangzhou (0.04)
  - Middle East > Jordan (0.04)
- Europe > Switzerland
  - Zürich > Zürich (0.14)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Information Technology > Security & Privacy (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.46)
    - Natural Language > Large Language Model (0.94)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)

Duplicate Docs Excel Report

Title
Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models

Similar Docs Excel Report more

Title	Similarity	Source
None found