Visible to the public Targeted Adversarial Examples for Black Box Audio Systems

TitleTargeted Adversarial Examples for Black Box Audio Systems
Publication TypeConference Paper
Year of Publication2019
AuthorsTaori, Rohan, Kamsetty, Amog, Chu, Brenton, Vemuri, Nikita
Conference Name2019 IEEE Security and Privacy Workshops (SPW)
Keywordsadversarial attack, adversarial generation, adversarial perturbations, Approximation algorithms, audio systems, audio transcription, automatic speech recognition systems, black box audio systems, Black Box Security, black-box, composability, Decoding, deep neural networks, deep recurrent networks, Estimation, fooling ASR systems, genetic algorithms, gradient estimation, gradient methods, Metrics, pubcrawl, recurrent neural nets, resilience, Resiliency, security of data, Sociology, Speech recognition, speech-to-text, Statistics, Task Analysis, white-box attacks
AbstractThe application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity, with 35% targeted attack success rate, after 3000 generations while maintaining 94.6% audio file similarity.
Citation Keytaori_targeted_2019