Boosting adversarial robustness using feature level stochastic smoothing

Addepalli, S and Jain, S and Sriramanan, G and Babu, RV (2021) Boosting adversarial robustness using feature level stochastic smoothing. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 19-25 June 2021, Nashville, pp. 93-102.

PDF IEEE_CVPRW _2021.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-of-the-art defenses is far from the requirements in critical applications such as robotics and autonomous navigation systems. Further, in practical use cases, network prediction alone might not suffice, and assignment of a confidence value for the prediction can prove crucial. In this work, we propose a generic method for introducing stochasticity in the network predictions, and utilize this for smoothing decision boundaries and rejecting low confidence predictions, thereby boosting the robustness on accepted samples. The proposed Feature Level Stochastic Smoothing based classification also results in a boost in robustness without rejection over existing adversarial training methods. Finally, we combine the proposed method with adversarial detection methods, to achieve the benefits of both approaches. © 2021 IEEE.

Item Type:	Conference Paper
Publication:	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher:	IEEE Computer Society
Additional Information:	The copyright for this article belongs to IEEE
Keywords:	Deep neural networks; Forecasting; Navigation systems; Robotics; Robots, Autonomous navigation systems; Confidence values; Critical applications; Feature level; Generic method; Network prediction; Practical use; Robotic navigation system; State of the art; Stochastics, Stochastic systems
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	07 Dec 2021 10:23
Last Modified:	07 Dec 2021 10:23
URI:	http://eprints.iisc.ac.in/id/eprint/70386

Actions (login required)

View Item