HotFlip: White-Box Adversarial Examples for Text Classification (2018 · 360 citations)
Character-level neural text classifiers can be fooled by tiny, nearly invisible edits, yet earlier NLP attacks mostly used black-box heuristics or random noise.
On Adversarial Examples for Character-Level Neural Machine Translation (2018 · 223 citations)
The paper asks how badly a character-level neural machine translation system can fail when an attacker sees its internals.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

HotFlip: White-Box Adversarial Examples for Text ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL)Javid Ebrahimi, Anyi Rao, Daniel Lowd, et al.2018 · 360 citations
On Adversarial Examples for Character-Level Neural Machine TranslationInternational Conference on Computational Linguistics (COLING)Javid Ebrahimi, Daniel Lowd, Dejing Dou2018 · 223 citations
How Can Self-Attention Networks Recognize Dyck-n Languages? ↗Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yetJavid Ebrahimi, Dhruv Gelda, Wei Zhang2020 · 39 citations

Co-authors here

2 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 426 times (of the 141,840 papers whose bibliographies we read); 51 citing papers with a page here →.

Updated 24 October 2026