Shadowcast: Stealthy Data Poisoning Attacks against Vision-Language Models

Nov-19-2025, 11:26:32 GMT–Neural Information Processing Systems

The first is a traditional Label Attack, tricking VLMs into misidentifying class labels, such as confusing Donald Trump for Joe Biden.

large language model, machine learning, natural language, (18 more...)

Neural Information Processing Systems

Nov-19-2025, 11:26:32 GMT

Conferences PDF

Country:
- Asia (0.04)
- North America > United States
  - Illinois > Champaign County
    - Urbana (0.04)
  - Maryland > Prince George's County
    - College Park (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Education > Health & Safety
  - School Nutrition (1.00)
- Government
  - Military (1.00)
  - Regional Government > North America Government
    - United States Government (1.00)
- Health & Medicine > Consumer Health (1.00)
- Information Technology > Security & Privacy (1.00)
- Leisure & Entertainment (0.94)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.94)
    - Natural Language > Large Language Model (0.70)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (0.93)

Duplicate Docs Excel Report

Title
6a2e30664b9647f97d7b9275358d083c-Paper-Conference.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found