Overlearning Reveals Sensitive Attributes · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1905.11742/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOverlearning Reveals Sensitive Attributes — mentioned by lmkghttps://news.ycombinator.com/item?id=22250657urn:hackerpapers:mention:1905.11742:22250657Wed, 05 Feb 2020 20:27:21 GMT<p>This is definitely true. In fact, this can be exploited to extract sensitive/private attributes about the training data from the learned models. This may become an issue for, e.g., AI in healthcare. &quot;Overlearning Reveals Sensitive Attributes&quot;: https://arxiv.org/abs/1905.11742</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.11742/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG