Proceedings of the 15th ACM Asia Conference on Computer and Communications Security 2020
DOI: 10.1145/3320269.3384733
|View full text |Cite
|
Sign up to set email alerts
|

SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems

Abstract: Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave. In this paper, we present SA, a new class of attacks to generate adversarial audios. Compared with existing attacks, SA highlights with a set of signicant features: (i) versatile-it is able to deceive a range of end-to-end acoustic systems under both white-box and black-box settings; (ii) eective-it is able to generate a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
79
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
3
3

Relationship

1
9

Authors

Journals

citations
Cited by 90 publications
(80 citation statements)
references
References 34 publications
1
79
0
Order By: Relevance
“…The focus of this work is systems built on musical data, which we attack using a white-box adversarial approach with full knowledge of the attacked systems. Despite most research having been conducted on image data, audio systems have also been shown to be vulnerable, e.g., by Carlini and Wagner (2018); Du et al (2020). Different approaches in the audio domain adapt attacks from the image domain (Subramanian et al, 2020) or use "psychoacoustic hiding" in an attempt to make adversarial perturbations as imperceptible as possible (Schönherr et al, 2019;Qin et al, 2019).…”
Section: Related Work and New Contributionsmentioning
confidence: 99%
“…The focus of this work is systems built on musical data, which we attack using a white-box adversarial approach with full knowledge of the attacked systems. Despite most research having been conducted on image data, audio systems have also been shown to be vulnerable, e.g., by Carlini and Wagner (2018); Du et al (2020). Different approaches in the audio domain adapt attacks from the image domain (Subramanian et al, 2020) or use "psychoacoustic hiding" in an attempt to make adversarial perturbations as imperceptible as possible (Schönherr et al, 2019;Qin et al, 2019).…”
Section: Related Work and New Contributionsmentioning
confidence: 99%
“…However, these systems can generate erroneous outputs that, e.g., lead to fatal acci dents [52]- [54]. To explore the robustness of AI software, a line of research has focused on attacking different systems that use deep neural networks, such as autonomous cars [25], [55] and speech recognition services [20], [56]. These work aim to fool AI software by feeding input with imperceptible perturba tions (i.e., adversarial examples).…”
Section: A Robustness Of a I Softwarementioning
confidence: 99%
“…We do not believe conventional wisdom could provide a "Panacea" at the moment. Inspired by [19] Adversarial examples were widely recognized to be a security concern for machine learning, and they are recently demonstrated to be equally effective in the audio domain [20], in the meantime, there were attempts to study them in audio tasks [21,22]. We are not only focusing on the security aspect of adversarial examples in this work, we also believe by going in the opposite direction of gradient descent (adversarial attack) we could potentially gain more insights.…”
Section: Background and Related Workmentioning
confidence: 99%