Information Leakage

Information Leakage is an error in machine learning model evaluation wherein data from outside the training dataset is inadvertently used during model development, leading to overestimated performance by violating the assumption of independent and identically distributed test conditions.

1.4K

Publications

66.7K

Citations

3.9K

Authors

1.1K

Institutions

Publications per year

2017–2026

716

Authors

3.9K

  1. HV
    H. Vincent Poor

    Princeton University, United States

    11 publications · 2.8K citations

    11

    h-index

  2. PM
    Pasquale Malacaria

    Queen Mary University of London, United Kingdom

    11 publications · 629 citations

    11

    h-index

  3. YH
    Yu‐ichi Hayashi

    Tohoku University, Japan

    11 publications · 292 citations

    11

    h-index

  4. CP
    Catuscia Palamidessi

    Laboratoire d'Informatique de l'École Polytechnique, France

    10 publications · 611 citations

    10

    h-index

  5. FP
    Flávio P. Calmon

    Harvard University Press, United States

    9 publications · 411 citations

    9

    h-index

1–5 of 3.9K

Venues

  1. 31

    h-index

  2. IEEE Access

    42 publications · 1.3K citations

    22

    h-index

  3. arXiv (Cornell University)

    Repository · 52 publications · 1.7K citations

    21

    h-index

  4. IEEE Transactions on Information Theory

    19 publications · 699 citations

    15

    h-index

  5. SSRN Electronic Journal

    Repository · 23 publications · 474 citations

    15

    h-index

1–5