Filters








72 Hits in 5.0 sec

Coverage-based Scene Fuzzing for Virtual Autonomous Driving Testing [article]

Zhisheng Hu, Shengjian Guo, Zhenyu Zhong, Kang Li
2021 arXiv   pre-print
We expect automated fuzzing will become a common practice in virtual testing for autonomous driving systems.  ...  Simulation-based virtual testing has become an essential step to ensure the safety of autonomous driving systems.  ...  A COVERAGE-BASED FUZZING SYSTEM FOR VIRTUAL SAFETY TESTING We propose ASF, a coverage-based fuzzing system to efficiently generate risky test cases for virtual safety testing. A.  ... 
arXiv:2106.00873v1 fatcat:dvms52rkavgxtnepslto35wsba

MDPFuzz: Testing Models Solving Markov Decision Processes [article]

Qi Pang, Yuanyuan Yuan, Shuai Wang
2022 arXiv   pre-print
However, these popular models for solving MDPs are neither thoroughly tested nor rigorously reliable. We present MDPFuzzer, the first blackbox fuzz testing framework for models solving MDPs.  ...  The Markov decision process (MDP) provides a mathematical framework for modeling sequential decision-making problems, many of which are crucial to security and safety, such as autonomous driving and robot  ...  ., an autonomous driving model makes decisions about each driving scene frame captured by its camera. Changing arbitrary frames may destroy inter-state coherence; see MDPFuzz's solution in Sec. 4.  ... 
arXiv:2112.02807v3 fatcat:ftksnewuyjcqfciepbjksb2e6e

Paracosm: A Test Framework for Autonomous Driving Simulations [chapter]

Rupak Majumdar, Aman Mathur, Marcus Pirron, Laura Stegner, Damien Zufferey
2021 Lecture Notes in Computer Science  
We present Paracosm, a framework for writing systematic test scenarios for autonomous driving simulations.  ...  We define a notion of test coverage for parameter configurations based on combinatorial testing and low dispersion sequences.  ...  We show a test generation strategy based on fuzzing that theoretically guarantees good coverage.  ... 
doi:10.1007/978-3-030-71500-7_9 fatcat:37yz2jr7ljevbkud77pzxkjm3y

Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems [article]

Ziyuan Zhong, Zhisheng Hu, Shengjian Guo, Xinyang Zhang, Zhenyu Zhong, Baishakhi Ray
2022 arXiv   pre-print
We define the failures (e.g., car crashes) caused by the faulty MSF as fusion errors and develop a novel evolutionary-based domain-specific search framework, FusED, for the efficient detection of fusion  ...  In general, these systems receive sensor data, compute driving decisions, and output control signals to the vehicles.  ...  We also want to thank colleagues from Baidu Security X-Lab and Chengzhi Mao from Columbia University for valuable discussions.  ... 
arXiv:2109.06404v3 fatcat:ln4ael6nu5cgvlgfleaa3lq34i

Autonomous Vehicles Scenario Testing Framework and Model of Computation: On Generation and Coverage

Alar J. Alnaser, Arman Sargolzaei, Mustafa Ilhan Akbas
2021 IEEE Access  
INDEX TERMS Autonomous Vehicles; Coverage; Model of Computation; Safety;Testing and Verification Framework VOLUME 4, 2016  ...  This paper focuses on defining the notion of coverage mathematically when using pseudo-randomly generated simulations for testing.  ...  RELATED WORK The most commonly used methodologies for providing coverage are search-based testing, pseudorandom test generation, and reinforcement learning-based test scenario generation.  ... 
doi:10.1109/access.2021.3074062 fatcat:4eoeqzumwjd77joydbrslndfw4

The State of Modeling, Simulation, and Data Utilization within Industry: An Autonomous Vehicles Perspective [article]

Joshua Fadaie
2019 arXiv   pre-print
In order for aviation based companies to adequately pursue disruptive mobility within real-world environments, be it in air or on the ground, modeling and simulation tools for autonomous vehicles provide  ...  The purpose of this paper is to address and decompose the simulation capabilities within the key players of the autonomous vehicle and self-driving car industry (Toyota, Waymo, BMW, Microsoft, NVIDIA,  ...  The sensor model is installed on a virtual vehicle in a simulated environment interacting with other vehicles to test performance and coverage.  ... 
arXiv:1910.06075v1 fatcat:k7d2tuj3lfer3c7psxm7pwgb3m

A Survey on Automated Driving System Testing: Landscapes and Trends [article]

Shuncheng Tang, Zhenya Zhang, Yi Zhang, Jixiang Zhou, Yan Guo, Shuang Liu, Shengjian Guo, Yan-Fu Li, Lei Ma, Yinxing Xue, Yang Liu
2022 arXiv   pre-print
Specifically, we make the following contributions: (1) we build a threat model that reveals the potential safety threats for each module of an ADS; (2) we survey the module-level testing techniques for  ...  Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry.  ...  187 5 autonomous car 85 1 autonomous vehicle 161 20 test/attack/verification/ autonomous driving 230 11 evaluation/validation/bug/analysis self-driving car 40 2 self-driving vehicle 24 0 driving/driver  ... 
arXiv:2206.05961v1 fatcat:fxntqw5asvhhzljee62vkmpkme

The Coming Era of AlphaHacking? A Survey of Automatic Software Vulnerability Detection, Exploitation and Patching Techniques [article]

Tiantian Ji, Yue Wu, Chang Wang, Xi Zhang, Zhongru Wang
2018 arXiv   pre-print
Utilizing automated system to detect, exploit and patch software vulnerabilities seems so attractive because of its scalability and cost-efficiency compared with the human expert based solution.  ...  With the success of the Cyber Grand Challenge (CGC) sponsored by DARPA, the topic of Autonomous Cyber Reasoning System (CRS) has recently attracted extensive attention from both industry and academia.  ...  Fuzzing does not require any program analysis so that it is fast and can generate multiple tests at the same time but with low coverage.  ... 
arXiv:1805.11001v2 fatcat:uh5ndhgmt5gpdk4opritn5fnsq

Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study [article]

Fitash Ul Haq, Donghwan Shin, Shiva Nejati, Lionel Briand
2019 arXiv   pre-print
We distinguish two general modes of testing for DNNs: Offline testing where DNNs are tested as individual units based on test datasets obtained independently from the DNNs under test, and online testing  ...  Though these questions are generally relevant to all autonomous systems, we study them in the context of automated driving systems where, as study subjects, we use DNNs automating end-to-end control of  ...  The latter issue is particularly critical since driving scenes, driving habits, as well as objects, infrastructures and roads in driving scenes, can vary widely across countries, continents, climates,  ... 
arXiv:1912.00805v1 fatcat:ktf5py26ljc5rjvjjtzuyefcs4

On Testing Machine Learning Programs [article]

Houssem Ben Braiek, Foutse Khomh
2018 arXiv   pre-print
Recently, software researchers have started adapting concepts from the software testing domain (e.g., code coverage, mutation testing, or property-based testing) to help ML engineers detect and correct  ...  Many people are now interacting with systems based on ML every day, e.g., voice recognition systems used by virtual personal assistants like Amazon Alexa or Google Home.  ...  Coverage-Guided Fuzzing. Odena and Goodfellow [38] developed a coverage-guided fuzzing framework specialized for testing neural networks.  ... 
arXiv:1812.02257v1 fatcat:yhomj6slnzeb5hp4xxww2ymaa4

Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review

Nijat Rajabli, Francesco Flammini, Roberto Nardone, Valeria Vittorini
2020 IEEE Access  
Autonomous, or self-driving, cars are emerging as the solution to several problems primarily caused by humans on roads, such as accidents and traffic congestion.  ...  for cyber-physical systems, and formal methods.  ...  A valuable systematic literature review on the specific topic of coverage-based testing for selfdriving autonomous vehicles is presented in reference [88] .  ... 
doi:10.1109/access.2020.3048047 fatcat:7mgx34zscvfavenyznqmbul7cm

A Systematic Survey of Attack Detection and Prevention in Connected and Autonomous Vehicles [article]

Trupil Limbasiya, Ko Zheng Teng, Sudipta Chattopadhyay, Jianying Zhou
2022 arXiv   pre-print
There are some surveys with a limited discussion on Attacks Detection and Prevention Systems (ADPS), but such surveys provide only partial coverage of different types of ADPS for CAVs.  ...  The number of Connected and Autonomous Vehicles (CAVs) is increasing rapidly in various smart transportation services and applications due to many benefits to society, people, and the environment.  ...  We thank LTA colleagues and project team members for their helpful input.  ... 
arXiv:2203.14965v1 fatcat:4orttcmbjfei5dbhsjnaovmm7a

Requirements-driven Test Generation for Autonomous Vehicles with Machine Learning Components [article]

Cumhur Erkan Tuncali, Georgios Fainekos, Danil Prokhorov, Hisahiro Ito, James Kapinski
2019 arXiv   pre-print
We present STL requirements for an autonomous vehicle system, which capture both component-level and system-level behaviors.  ...  Autonomous vehicles are complex systems that are challenging to test and debug.  ...  SIM-ATAV FRAMEWORK We describe Sim-ATAV, a framework for performing testing and analysis of autonomous driving systems in a virtual environment.  ... 
arXiv:1908.01094v1 fatcat:b65tzewderajrkeiukezvlbiga

Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies [article]

Aizaz Sharif, Dusica Marijan
2022 arXiv   pre-print
Our results show that adversarial testing can be used for finding erroneous autonomous driving behavior, followed by adversarial training for improving the robustness of deep reinforcement learning based  ...  To effectively defend against adversaries, it is required to not only test autonomous cars for finding driving errors, but to improve the robustness of the cars to these errors.  ...  The authors in [11] uses search-based testing technique to automatically create challenging virtual scenarios for testing self-driving cars.  ... 
arXiv:2112.11937v2 fatcat:74tsuibo2jeqnpefl7lazo7o2a

A Survey on Recent Advanced Research of CPS Security

Zhenhua Wang, Wei Xie, Baosheng Wang, Jing Tao, Enze Wang
2021 Applied Sciences  
, block coverage, and edge coverage.  ...  After testing on 288 images, the evaluation results show that the throughput of FIRM-AFL can find 1-day or 0-day vulnerabilities 8.2 times higher than system-mode emulation-based fuzzing on average.  ... 
doi:10.3390/app11093751 fatcat:fxby2wjzpnchrfshvilxalmptm
« Previous Showing results 1 — 15 out of 72 results