Feature Purification: How Adversarial Training Performs Robust Deep Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2005.10190/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTFeature Purification: How Adversarial Training Performs Robust Deep Learning — mentioned by MindGodshttps://news.ycombinator.com/item?id=23691630urn:hackerpapers:mention:2005.10190:23691630Tue, 30 Jun 2020 16:17:40 GMT<p>Paper: &quot;Feature Purification: How Adversarial Training Performs Robust Deep Learning&quot; https://arxiv.org/abs/2005.10190</p><p><a href="https://hackerpaper.kaipfister.de/p/2005.10190/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG