Departmental Papers (CIS)
Date of this Version
5-2021
Document Type
Conference Paper
Recommended Citation
Yiannis Kantaros, Taylor Carpenter, Kaustubh Sridhar, Yahan Yang, Insup Lee, and James Weimer, "Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems", Proceedings of ACM/IEEE International Conference on Cyber-physical Systems (ICCPS 2021) . May 2021. http://dx.doi.org/10.1145/3450267.3450535
Abstract
Deep neural network (DNN) models have proven to be vulnerable to adversarial digital and physical attacks. In this paper, we propose a novel attack- and dataset-agnostic and real-time detector for both types of adversarial inputs to DNN-based perception systems. In particular, the proposed detector relies on the observation that adversarial images are sensitive to certain label-invariant transformations. Specifically, to determine if an image has been adversarially manipulated, the proposed detector checks if the output of the target classifier on a given input image changes significantly after feeding it a transformed version of the image under investigation. Moreover, we show that the proposed detector is computationally-light both at runtime and design-time which makes it suitable for real-time applications that may also involve large-scale image domains. To highlight this, we demonstrate the efficiency of the proposed detector on ImageNet, a task that is computationally challenging for the majority of relevant defenses, and on physically attacked traffic signs that may be encountered in real-time autonomy applications. Finally, we propose the first adversarial dataset, called AdvNet that includes both clean and physical traffic sign images. Our extensive comparative experiments on the MNIST, CIFAR10, ImageNet, and AdvNet datasets show that VisionGuard outperforms existing defenses in terms of scalability and detection performance. We have also evaluated the proposed detector on field test data obtained on a moving vehicle equipped with a perception-based DNN being under attack.
Subject Area
CPS Safe Autonomy, CPS Security
Publication Source
Proceedings of ACM/IEEE International Conference on Cyber-physical Systems (ICCPS 2021)
DOI
10.1145/3450267.3450535
Keywords
computer systems organization, real-time systems, computing methodologies, computer vision
Date Posted: 10 January 2023
This document has been peer reviewed.
Comments
ACM/IEEE International Conference on Cyber-physical Systems (ICCPS 2021), Nashville, TN, May 2021