the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2016

    Deep Learning with Differential Privacy

    Martín Abadi (first author) · 2016

    Read the original

    DOI 10.1145/2976749.2978318arXiv 1607.00133OpenAlex W2473418344

    On the reading lists

    Why it matters

    Introduced practical differentially private deep learning using gradient clipping and calibrated noise.

    Condensed from the expert lists' notes.

    The record

    First released
    2016 (from arXiv 1607.00133)
    Citations
    8,604 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.589 · computed rank 160 · consensus 0.78, must-read 0.5, citations percentile 0.872 (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.