Pith. sign in

REVIEW

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.15283 v1 pith:V5RY3SHW submitted 2022-03-29 eess.AS cs.LG

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems

classification eess.AS cs.LG
keywords defensesattacksspeechadversarialdomaindeepmdnfmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applications such as automatic speech recognition (ASR) are increasingly relying on deep learning models, and so are also prone to adversarial attacks. However, many of the defenses explored for ASR simply adapt the image-domain defenses, which may not provide optimal robustness. This paper explores speech specific defenses using the mel spectral domain, and introduces a novel defense method called 'mel domain noise flooding' (MDNF). MDNF applies additive noise to the mel spectrogram of a speech utterance prior to re-synthesising the audio signal. We test the defenses against strong white-box adversarial attacks such as projected gradient descent (PGD) and Carlini-Wagner (CW) attacks, and show better robustness compared to a randomized smoothing baseline across strong threat models.

discussion (0)

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