the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2017

    Towards Deep Learning Models Resistant to Adversarial Attacks

    Aleksander Madry (first author) · 2017 · published 2018

    Read the original

    arXiv 1706.06083OpenAlex W2640329709

    On the reading lists

    Why it matters

    Established robust optimization and PGD adversarial training as central robustness baselines.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from arXiv 1706.06083)
    Published
    2018
    Citations
    15,844 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.616 · computed rank 135 · consensus 0.77, must-read 0.5, citations percentile 0.957 (2010s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.