Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1907.11932/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTIs BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment — mentioned by meiji163https://news.ycombinator.com/item?id=29381096urn:hackerpapers:mention:1907.11932:29381096Mon, 29 Nov 2021 15:43:33 GMT<p>Language models have the same defect - they are quite brittle and susceptible to black-box adversarial attacks ( eg arxiv.org/abs/1907.11932 )</p><p><a href="https://hackerpaper.kaipfister.de/p/1907.11932/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL