Adversarial Attack Detection

Adversarial Attack Detection is a systematic method in imaging informatics security that identifies manipulated inputs designed to deceive machine learning models by distinguishing them from legitimate data through anomaly analysis in image-based model behavior.

837

Publications

49.7K

Citations

2.8K

Authors

782

Institutions

Publications per year

2017–2026

813

Authors

2.8K

  1. GT
    Guanhong Tao

    Purdue University West Lafayette, United States

    8 publications · 868 citations

    8

    h-index

  2. MV
    Mayank Vatsa

    Indraprastha Institute of Information Technology Delhi, India

    7 publications · 307 citations

    7

    h-index

  3. RS
    Richa Singh

    Indraprastha Institute of Information Technology Delhi, India

    7 publications · 307 citations

    7

    h-index

  4. TG
    Tom Goldstein

    University of Maryland, College Park, United States

    7 publications · 462 citations

    7

    h-index

  5. AA
    Akshay Agarwal

    Indraprastha Institute of Information Technology Delhi, India

    7 publications · 307 citations

    7

    h-index

1–5 of 2.8K

Venues

  1. arXiv (Cornell University)

    Repository · 144 publications · 8K citations

    40

    h-index

  2. Computers & Security

    28 publications · 1.2K citations

    21

    h-index

  3. IEEE Access

    19 publications · 831 citations

    17

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 19 publications · 975 citations

    17

    h-index

  5. 14

    h-index

1–5