Data Poisoning Attacks

Data Poisoning Attack is a type of adversarial manipulation in federated learning wherein a malicious participant intentionally introduces corrupted or misleading data during the training process to compromise the integrity, accuracy, or convergence of the global model.

342

Publications

23.3K

Citations

1.1K

Authors

334

Institutions

Publications per year

2017–2026

331

Variants

Data Poisoning Attack

Authors

1.1K

  1. TG
    Tom Goldstein

    University of Maryland, College Park, United States

    14 publications · 873 citations

    12

    h-index

  2. NZ
    Neil Zhenqiang Gong

    Duke University, United States

    11 publications · 943 citations

    11

    h-index

  3. BB
    Battista Biggio

    University of Cagliari, Italy

    10 publications · 2.8K citations

    10

    h-index

  4. LF
    Liam Fowl

    University of Maryland, College Park, United States

    9 publications · 232 citations

    9

    h-index

  5. JG
    Jonas Geiping

    University of Maryland, College Park, United States

    9 publications · 228 citations

    9

    h-index

1–5 of 1.1K

Venues

  1. arXiv (Cornell University)

    Repository · 73 publications · 6.3K citations

    35

    h-index

  2. IEEE Internet of Things Journal

    8 publications · 913 citations

    10

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 9 publications · 625 citations

    10

    h-index

  4. IEEE Transactions on Industrial Informatics

    10 publications · 1.1K citations

    10

    h-index

  5. IEEE Access

    5 publications · 553 citations

    8

    h-index

1–5