HackerPapers

arXiv:1801.01944cs.LG

Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

Nicholas Carlini, David Wagner

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.

arXiv comments
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.AIArtificial Intelligence cs.CRCryptography and Security

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jan 2024 to Jan 2024. Found in 3 HN submissions from Jan 2018 to Jan 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Attacks on machine learning models 1 comment

    • Decent write up :+1: Recommend reading on the topic - Biggio & Rolia "Wild Patterns" review paper for the thorough security perspective (and historical accuracy cough): https://arxiv.org/pdf/1712.03141.pdf - Carlini & Wagner attack a.k.a. the gold standard of adversarial machine…

      dijksterhuisView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.