the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2016

    Towards Evaluating the Robustness of Neural Networks

    Nicholas Carlini (first author) · 2016

    Read the original

    DOI 10.1109/sp.2017.49arXiv 1608.04644OpenAlex W2516574342

    On the reading lists

    Why it matters

    Introduced powerful optimization-based attacks that became standard robustness evaluation tools.

    Condensed from the expert lists' notes.

    The record

    First released
    2016 (from arXiv 1608.04644)
    Citations
    10,423 citations, as counted by Semantic Scholar logoSemantic Scholar (non-commercial licence)
    Named by
    both expert lists
    Score
    0.482 · computed rank 251 · consensus 0.54, must-read 0, citations percentile 0.915 (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), and Semantic Scholar logoSemantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.