Recognition of sounds using square cauchy mixture distribution

Ito, Akinori

doi:10.1109/siprocess.2016.7888359

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Cauchy noise: similar to gaussian noise and its bell shaped curve, the Cauchy noise distinguishes itself by presenting a density function with a shape that has a higher density at center and also has a longer tail [46]. While all of these noises can be used by an adversary, we chose white noise as type of audio disturbance, since this noisy variant is widely adopted by different research across [27], [73], [101].…”

Section: Evasion Attacksmentioning

confidence: 99%

Audio Attacks and Defenses against AED Systems -- A Practical Study

Santos¹,

Nilizadeh²

2021

Preprint

View full text Add to dashboard Cite

Audio Event Detection (AED) Systems capture audio from the environment and employ some deep learning algorithms for detecting the presence of a specific sound of interest. In this paper, we evaluate deep learning-based AED systems against evasion attacks through adversarial examples. We run multiple security critical AED tasks, implemented as CNNs classifiers, and then generate audio adversarial examples using two different types of noise, namely background and white noise, that can be used by the adversary to evade detection. We also examine the robustness of existing third-party AED capable devices, such as Nest devices manufactured by Google, which run their own black-box deep learning models.We show that an adversary can focus on audio adversarial inputs to cause AED systems to misclassify, similarly to what has been previously done by works focusing on adversarial examples from the image domain. We then, seek to improve classifiers' robustness through countermeasures to the attacks. We employ adversarial training and a custom denoising technique. We show that these countermeasures, when applied to audio input, can be successful, either in isolation or in combination, generating relevant increases of nearly fifty percent in the performance of the classifiers when these are under attack.

show abstract