the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2018

    Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

    Anish Athalye (first author) · 2018

    Read the original

    arXiv 1802.00420OpenAlex W2787708942

    On the reading lists

    Why it matters

    Exposed gradient masking and fundamentally improved standards for evaluating adversarial defenses.

    Condensed from the expert lists' notes.

    The record

    First released
    2018 (from arXiv 1802.00420)
    Citations
    2,171 citations, as counted by OpenAlex (CC0)
    Named by
    the chatgpt list only
    Score
    0.289 · computed rank 630 · consensus 0.22, must-read 0, citations percentile 0.638 (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.