When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time

标题
When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time
作者
关键词
-
出版物
NEURAL COMPUTATION
Volume 31, Issue 8, Pages 1624-1670
出版商
MIT Press - Journals
发表日期
2019-07-02
DOI
10.1162/neco_a_01209

向作者/读者发起求助以获取更多资源

Publish scientific posters with Peeref

Peeref publishes scientific posters from all research disciplines. Our Diamond Open Access policy means free access to content and no publication fees for authors.

Learn More

Ask a Question. Answer a Question.

Quickly pose questions to the entire community. Debate answers and get clarity on the most important issues facing researchers.

Get Started