Write a Blog >>
ICSE 2020
Wed 24 June - Thu 16 July 2020
Tue 7 Jul 2020 15:12 - 15:24 at Baekje - A1-Autonomous Driving Systems Chair(s): Donghwan Shin

Deep Neural Networks (DNNs) have been widely applied in autonomous systems such as self-driving vehicles. Recently, DNN testing has been intensively studied to automatically generate adversarial examples, which inject small-magnitude perturbations into inputs to test DNNs under extreme situations. While existing testing techniques prove to be effective, particularly for autonomous driving, they mostly focus on generating digital adversarial perturbations, e.g., changing image pixels, which may never happen in the physical world. Thus, there is a critical missing piece in the literature on autonomous driving testing: understanding and exploiting both digital and physical adversarial perturbation generation for impacting steering decisions. In this paper, we propose a systematic physical-world testing approach, namely DeepBillboard, targeting at a quite common and practical driving scenario: drive-by billboards. DeepBillboard is capable of generating a robust and resilient printable adversarial billboard test, which works under dynamic changing driving conditions including viewing angle, distance, and lighting. The objective is to maximize the possibility, degree, and duration of the steering-angle errors of an autonomous vehicle driving by our generated adversarial billboard. We have extensively evaluated the efficacy and robustness of DeepBillboard by conducting both experiments with digital perturbations and physical-world case studies. The digital experimental results show that DeepBillboard is effective for various steering models and scenes. Furthermore, the physical case studies demonstrate that DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions, being able to mislead the average steering angle error up to 26.44 degrees. To the best of our knowledge, this is the first study demonstrating the possibility of generating realistic and continuous physical-world tests for practical autonomous driving systems; moreover, DeepBillboard can be directly generalized to a variety of other physical entities/surfaces along the curbside, e.g., a graffiti painted on a wall.

Tue 7 Jul

Displayed time zone: (UTC) Coordinated Universal Time change

15:00 - 16:00
A1-Autonomous Driving SystemsTechnical Papers at Baekje
Chair(s): Donghwan Shin University of Luxembourg (SnT)
15:00
12m
Talk
SLEMI: Equivalence Modulo Input (EMI) Based Mutation of CPS Models for Finding Compiler Bugs in SimulinkArtifact ReusableTechnicalArtifact Available
Technical Papers
Shafiul Azam Chowdhury University of Texas at Arlington, Sohil Lal Shrestha The University of Texas at Arlington, Taylor T Johnson Vanderbilt University, Christoph Csallner University of Texas at Arlington
Link to publication DOI Media Attached
15:12
12m
Talk
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving SystemsTechnical
Technical Papers
Husheng Zhou The University of Texas at Dallas, Wei Li Southern University of Science and Technology, Zelun Kong The University of Texas at Dallas, Junfeng Guo The University of Texas at Dallas, Yuqun Zhang Southern University of Science and Technology, Lingming Zhang The University of Texas at Dallas, Bei Yu The Chinese University of Hong Kong, Cong Liu UT Dallas
15:24
12m
Talk
Misbehaviour Prediction for Autonomous Driving SystemsTechnical
Technical Papers
Andrea Stocco Università della Svizzera italiana, Michael Weiss Università della Svizzera Italiana (USI), Marco Calzana Università della Svizzera Italiana (USI), Paolo Tonella Università della Svizzera italiana
Pre-print
15:36
12m
Talk
Approximation-Refinement Testing of Compute-Intensive Cyber-Physical Models: An Approach Based on System IdentificationArtifact ReusableTechnicalArtifact Available
Technical Papers
Claudio Menghi University of Luxembourg, Shiva Nejati University of Ottawa, Lionel Briand SnT Centre/University of Luxembourg, Yago Isasi Parache LuxSpace
15:48
12m
Talk
A Comprehensive Study of Autonomous Vehicle BugsTechnical
Technical Papers
Joshua Garcia University of California, Irvine, Yang Feng Nanjing University, Junjie Shen University of California, Irvine, Sumaya Almanee University of California, Irvine, Yuan Xia University of California, Irvine, Qi Alfred Chen University of California, Irvine