Concepedia

Adversarial Examples

Adversarial Examples is a type of input instance in image classification that belongs to the category of deliberately perturbed data points, distinguished by imperceptible modifications designed to mislead machine learning models into making incorrect predictions while appearing indistinguishable from original inputs to human observers.

2.2K

Publications

189.5K

Citations

5.7K

Authors

1.1K

Institutions

Publications per year

2017–2026

2.1K

Parents

Publications

2.2K

Explaining and Harnessing Adversarial Examples

Ian Goodfellow, Jonathon Shlens, Christian Szegedy · arXiv (Cornell University) · 2014 · 8.2K citations · Full text

, , +11

mixup: Beyond Empirical Risk Minimization

Hongyi Zhang, Moustapha Cissé, Yann Dauphin et al. · arXiv (Cornell University) · 2017 · 4.8K citations · Full text

, , +13

On Assessing ML Model Robustness: A Methodological Framework (Academic Track)

Dagstuhl Research Online Publication Server · 2025 · 4.6K citations · Full text

, , +10

Practical Black-Box Attacks against Machine Learning

Nicolas Papernot, Patrick McDaniel, Ian Goodfellow et al. · 2017 · 3.5K citations

, , +10

Boosting Adversarial Attacks with Momentum

Yinpeng Dong, Fangzhou Liao, Tianyu Pang et al. · 2018 · 2.9K citations

, , +8

1–5 of 2.2K

Authors

5.7K

  1. DS
    Dawn Song

    University of California, Berkeley, United States

    37 publications · 9.4K citations

    32

    h-index

  2. CH
    Cho‐Jui Hsieh

    University of California, Los Angeles, United States

    34 publications · 3.1K citations

    27

    h-index

  3. PC
    Pin‐Yu Chen

    IBM (United States), United States

    41 publications · 3.3K citations

    27

    h-index

  4. NC
    Nicholas Carlini

    Google (United States), United States

    31 publications · 6.8K citations

    25

    h-index

  5. NP
    Nicolas Papernot

    University of Toronto, Canada

    28 publications · 10.1K citations

    25

    h-index

1–5 of 5.7K

Institutions

1.1K

  1. University of California, Berkeley

    Berkeley, United States

    43 h-index

    137 publications

    38.2K citations

  2. Tsinghua University

    Beijing, China

    38 h-index

    228 publications

    39.4K citations

  3. Massachusetts Institute of Technology

    Cambridge, United States

    32 h-index

    76 publications

    21.9K citations

  4. Google (United States)

    Mountain View, United States

    32 h-index

    99 publications

    38.8K citations

  5. Chinese Academy of Sciences

    Beijing, China

    31 h-index

    139 publications

    7K citations

  6. University of California, Los Angeles

    Los Angeles, United States

    28 h-index

    76 publications

    10.3K citations

  7. Stanford University

    Stanford, United States

    26 h-index

    54 publications

    11.3K citations

  8. Tencent (China)

    Shenzhen, China

    26 h-index

    87 publications

    7.3K citations

1–8 of 1.1K

Venues

  1. arXiv (Cornell University)

    Repository · 707 publications · 67.9K citations

    114

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 70 publications · 6.3K citations

    37

    h-index

  3. 24

    h-index

  4. IEEE Access

    33 publications · 3.3K citations

    22

    h-index

  5. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 24 publications · 1.4K citations

    21

    h-index

1–5