Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1911.07101/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTGlyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data — mentioned by nindanaotohttps://news.ycombinator.com/item?id=22866141urn:hackerpapers:mention:1911.07101:22866141Tue, 14 Apr 2020 14:08:14 GMT<p>TFHE is known to be switchable between other RLWE based Homomorphic Encryption. https://eprint.iacr.org/2018/758 Glyph applied it to accelerate deep learning, but they use integer level, not float. https://arxiv.org/abs/1911.07101 AFAIK, Homomorphic Encryption which supports floating point arithmetic is not known. Fixed point one is known, CKKS. https://github.com/snucrypto/HEAAN</p><p><a href="https://hackerpaper.kaipfister.de/p/1911.07101/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG