SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2007.06622/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems — mentioned by dijksterhuishttps://news.ycombinator.com/item?id=27716081urn:hackerpapers:mention:2007.06622:27716081Fri, 02 Jul 2021 19:57:53 GMT<p>The research side of &quot;minimum modifications required&quot; is with not quite there yet [0]. Audio source separation for now is probably the way to go (see other child comment). Although I imagine it would encounter similar problems with &quot;over the air&quot; type environments. Black box transfers require large, audibly noticeable modifications. see &quot;Transfer attacks against YouTube’s Content ID&quot; audio example in [0]. Most work has focused on speech recognition, so see final appendix in [1], the authors of which are currently looking at the problem in more detail (stay tuned for results). Also…</p><p><a href="https://hackerpaper.kaipfister.de/p/2007.06622/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR