Explore the fascinating world of audio adversarial examples in this 25-minute IEEE conference talk presented at the 1st Deep Learning and Security Workshop. Delve into the construction of targeted attacks on automatic speech recognition systems, specifically focusing on Mozilla's DeepSpeech implementation. Discover how audio waveforms can be manipulated to be 99.9% similar to the original while transcribing as any chosen phrase, with the ability to recognize up to 50 characters per second. Gain insights into the white-box iterative optimization-based attack methodology and its 100% success rate. Understand the implications of this new domain in the study of adversarial examples and its potential impact on speech-to-text technology security.
Audio Adversarial Examples - Targeted Attacks on Speech-to-Text
Overview
Syllabus
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Targeted Adversarial Examples for Black Box Audio Systems
-
Adversarial Examples for Proof-of-Learning
-
Hear "No Evil", See "Kenansville" - Efficient and Transferable Black-Box Attacks on Automatic Speech Recognition Systems
-
AI-Guardian - Defeating Adversarial Attacks Using Backdoors
-
Adversarial and Poisoning Attacks Against Speech Systems - Where to Find Them
-
JARVIS Never Saw It Coming - Hacking Machine Learning in Speech, Text and Face Recognition
