Loading [a11y]/accessibility-menu.js
Towards Robust Compressed Convolutional Neural Networks | IEEE Conference Publication | IEEE Xplore
Scheduled Maintenance: On Tuesday, 25 February, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (1800-2200 UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

Towards Robust Compressed Convolutional Neural Networks


Abstract:

Recent studies on robustness of Convolutional Neural Network (CNN) shows that CNNs are highly vulnerable towards adversarial attacks. Meanwhile, smaller sized CNN models ...Show More

Abstract:

Recent studies on robustness of Convolutional Neural Network (CNN) shows that CNNs are highly vulnerable towards adversarial attacks. Meanwhile, smaller sized CNN models with no significant accuracy loss are being introduced to mobile devices. However, only the accuracy on standard datasets is reported along with such research. The wide deployment of smaller models on millions of mobile devices stresses importance of their robustness. In this research, we study how robust such models are with respect to state-of-the-art compression techniques such as quantization. Our contributions include: (1) insights to achieve smaller models and robust models (2) a compression framework which is adversarial-aware. In the former, we discovered that compressed models are naturally more robust than compact models. This provides an incentive to perform compression rather than designing compact models. Additionally, the latter provides benefits of increased accuracy and higher compression rate, up to 90×.
Date of Conference: 27 February 2019 - 02 March 2019
Date Added to IEEE Xplore: 04 April 2019
ISBN Information:

ISSN Information:

Conference Location: Kyoto, Japan

References

References is not available for this document.