pith. sign in

arxiv: 1811.01312 · v2 · pith:L7VNWYIRnew · submitted 2018-11-04 · 💻 cs.CR · cs.LG· cs.NE

Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization

classification 💻 cs.CR cs.LGcs.NE
keywords systemsadversarialattacksblack-boxautomaticevolutionaryframeworkmodel
0
0 comments X
read the original abstract

Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either replicate the model itself or to craft examples which cause the model to fail. In this work, we propose a framework which uses multi-objective evolutionary optimization to perform both targeted and un-targeted black-box attacks on Automatic Speech Recognition (ASR) systems. We apply this framework on two ASR systems: Deepspeech and Kaldi-ASR, which increases the Word Error Rates (WER) of these systems by upto 980%, indicating the potency of our approach. During both un-targeted and targeted attacks, the adversarial samples maintain a high acoustic similarity of 0.98 and 0.97 with the original audio.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.