Robotic systems are no longer simply built and designed to perform sequential repetitive tasks primarily in a static manufacturing environment. Systems such as autonomous vehicles make use of intricate machine learning algorithms to adapt their behavior to dynamic conditions in their operating environment. These machine learning algorithms provide an additional attack surface for an adversary to exploit in order to perform a cyberattack. Since an attack on robotic systems such as autonomous vehicles have the potential to cause great damage and harm to humans, it is essential that detection and defenses of these attacks be explored. This paper discusses the plausibility of direct and indirect cyberattacks on a machine learning model through the use of a virtual autonomous vehicle operating in a simulation environment using a machine learning model for control. Using this vehicle, this paper proposes various methods of detection of cyberattacks on its machine learning model and discusses possible defense mechanisms to prevent such attacks.
FaheyKMMillerMJ. Unmanned systems integrated roadmap 2017-2042. Arlington, VA: Department of Defense, 2017.
3.
BiggioBCoronaINelsonB, et al. Security evaluation of support vector machines in adversarial environments. In: MaYGuoG (eds) Support vector machines applications. Berlin; Heidelberg: Springer, 2014, pp. 105–153.
HuangLJosephADNelsonB, et al. Adversarial machine learning. In: Proceedings of the 4th ACM workshop on security and artificial intelligence, Chicago, IL, 21 October 2011, pp. 43–58. New York: ACM.
6.
ClarkGWAndelTRDoranMV. Simulation-based reduction of operational and cybersecurity risks in autonomous vehicles. In: Proceedings of the 2019 IEEE conference on cognitive and computational aspects of situation management (CogSIMA), Las Vegas, NV, 8–11 April 2019, pp. 140–146, 2019. New York: IEEE.
7.
Martin-DominguezA. Modelado y Simulacion de un Robot LEGO Mindstorms EV3 mediante V-REP y Matlab. PhD Thesis, University of Málaga, Málaga, 2016.
SarhadiPYousefpourS. State of the art: hardware in the loop modeling and simulation with its applications in design, development and implementation of system and control software. Int J Dynam Control2015; 3: 470–479.
ClarkGWDoranMGlissonW. A malicious attack on the machine learning policy of a robotic system. In: Proceedings of the 2018 17th IEEE international conference on trust, security and privacy in computing and communications; 12th IEEE international conference on big data science and engineering (TrustCom/BigDataSE), New York, 1–3 August 2018, pp. 516–521. New York: IEEE.
12.
SzeVChenY-HYangT-J, et al. Efficient processing of deep neural networks: a tutorial and survey. P IEEE2017; 105: 2295–2329.
13.
HeatonJ. Introduction to neural networks with Java. St. Louis, MO: Heaton Research, Inc., 2008.
14.
IdeHKuritaT. Improvement of learning for CNN with ReLU activation by sparse regularization. In: Proceedings of the 2017 international joint conference on neural networks (IJCNN), Anchorage, AK, 14–19 May 2017, pp. 2684–2691. New York: IEEE.
15.
HeKZhangXRenS, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE international conference on computer vision, Santiago, 7–13 December 2015, pp. 1026–1034. New York: IEEE.
SuttonRSBartoAG. Reinforcement learning: an introduction, vol. 1. Cambridge, MA: The MIT Press, 1998.
20.
PapernotNMcDanielPSinhaA, et al. Towards the science of security and privacy in machine learning, 2016, https://arxiv.org/abs/1611.03814
21.
SharifMBhagavatulaSBauerL, et al. Accessorize to a crime: real and stealthy attacks on state-of-the-art face recognition. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, Vienna, 24–28 October 2016, pp. 1528–1540. New York: ACM.
PetitJStottelaarBFeiriM, et al. Remote attacks on automated vehicles sensors: experiments on camera and LiDAR. In: Proceedings of the black hat Europe, Amsterdam, 10–13 November 2015, vol. 11. Black Hat.
