the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2023

    Universal and Transferable Adversarial Attacks on Aligned Language Models

    Andy Zou (first author) · 2023

    Read the original

    arXiv 2307.15043OpenAlex W4385374425

    On the reading lists

    Why it matters

    Introduced automated adversarial suffixes capable of transferring jailbreaks across language models.

    Condensed from the expert lists' notes.

    The record

    First released
    2023 (from arXiv 2307.15043)
    Citations
    3,892 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    the chatgpt list only
    Score
    0.353 · computed rank 470 · consensus 0.06, must-read 0, citations percentile 0.957 (2020s · 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.