TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Targeted Attacks on Speech-to-Text [pdf]

4 pointsby khcover 7 years ago

1 comment

kleer001over 7 years ago
If asked I would have answered yes, of course this is possible, but it never occurred to me. I wonder if these adversarial attacks are possible in ML because there's too much overfitting in the models or they're too high rez or? Can someone in this space help me grow a better intuition of how these work?