From hero to zéroe: A benchmark of low-level adversarial attacks

S Eger, Y Benz - Proceedings of the 1st conference of the Asia …, 2020 - aclanthology.org
Adversarial attacks are label-preserving modifications to inputs of machine learning
classifiers designed to fool machines but not humans. Natural Language Processing (NLP) …
被引用次数：37 相关文章

From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks

S Eger, Y Benz - arXiv e-prints, 2020 - ui.adsabs.harvard.edu
Adversarial attacks are label-preserving modifications to inputs of machine learning
classifiers designed to fool machines but not humans. Natural Language Processing (NLP) …

From Hero to Z\'eroe: A Benchmark of Low-Level Adversarial Attacks

S Eger, Y Benz - arXiv preprint arXiv:2010.05648, 2020 - arxiv.org
Adversarial attacks are label-preserving modifications to inputs of machine learning
classifiers designed to fool machines but not humans. Natural Language Processing (NLP) …