Wei Jia (School of Cyber Science and Engineering, Huazhong University of Science and Technology), Zhaojun Lu (School of Cyber Science and Engineering, Huazhong University of Science and Technology), Haichun Zhang (Huazhong University of Science and Technology), Zhenglin Liu (Huazhong University of Science and Technology), Jie Wang (Shenzhen Kaiyuan Internet Security Co., Ltd), Gang Qu (University of Maryland)

Adversarial Examples (AEs) can deceive Deep Neural Networks (DNNs) and have received a lot of attention recently. However, majority of the research on AEs is in the digital domain and the adversarial patches are static. Such research is very different from many real-world DNN applications such as Traffic Sign Recognition (TSR) systems in autonomous vehicles. In TSR systems, object detectors use DNNs to process streaming video in real time. From the view of object detectors, the traffic sign’s position and quality of the video are continuously changing, rendering the digital AEs ineffective in the physical world.

In this paper, we propose a systematic pipeline to generate robust physical AEs against real-world object detectors. Robustness is achieved in three ways. First, we simulate the in-vehicle cameras by extending the distribution of image transformations with the blur transformation and the resolution transformation. Second, we design the single and multiple bounding boxes filters to improve the efficiency of the perturbation training. Third, we consider four representative attack vectors, namely Hiding Attack (HA), Appearance Attack (AA), Non-Target Attack (NTA) and Target Attack (TA). For each of them, a loss function is defined to minimize the impact of the fabrication process on the physical AEs.

We perform a comprehensive set of experiments under a variety of environmental conditions by varying the distance from $0m$ to $30m$, changing the angle from $-60^{circ}$ to $60^{circ}$, and considering illuminations in sunny and cloudy weather as well as at night. The experimental results show that the physical AEs generated from our pipeline are effective and robust when attacking the YOLO v5 based TSR system. The attacks have good transferability and can deceive other state-of-the-art object detectors. We launched HA and NTA on a brand-new 2021 model vehicle. Both attacks are successful in fooling the TSR system, which could be a lifethreatening case for autonomous vehicles. Finally, we discuss three defense mechanisms based on image preprocessing, AEs detection, and model enhancing.

View More Papers

SpiralSpy: Exploring a Stealthy and Practical Covert Channel to...

Zhengxiong Li (University at Buffalo, SUNY), Baicheng Chen (University at Buffalo), Xingyu Chen (University at Buffalo), Huining Li (SUNY University at Buffalo), Chenhan Xu (University at Buffalo, SUNY), Feng Lin (Zhejiang University), Chris Xiaoxuan Lu (University of Edinburgh), Kui Ren (Zhejiang University), Wenyao Xu (SUNY Buffalo)

Read More

Fuzzing Configurations of Program Options

Zenong Zhang (University of Texas at Dallas), George Klees (University of Maryland), Eric Wang (Poolesville High School), Michael Hicks (University of Maryland), Shiyi Wei (University of Texas at Dallas)

Read More

RVPLAYER: Robotic Vehicle Forensics by Replay with What-if Reasoning

Hongjun Choi (Purdue University), Zhiyuan Cheng (Purdue University), Xiangyu Zhang (Purdue University)

Read More

WIP: On Robustness of Lane Detection Models to Physical-World...

Takami Sato (UC Irvine) and Qi Alfred Chen (UC Irvine)

Read More