Machine Learning Based Runtime Detection and Recovery Method Against UAV Sensor Attacks

Sun Cong; Zeng Huiming; Song Huandong; Wang Yunbo; Zhang Zongxu; Ma Jianfeng

doi:10.7544/issn1000-1239.202330451

Journal of Computer Research and Development > 2023 > 60(10): 2291-2303. > DOI: 10.7544/issn1000-1239.202330451 CSTR: 32373.14.issn1000-1239.202330451

Sun Cong, Zeng Huiming, Song Huandong, Wang Yunbo, Zhang Zongxu, Ma Jianfeng. Machine Learning Based Runtime Detection and Recovery Method Against UAV Sensor Attacks[J]. Journal of Computer Research and Development, 2023, 60(10): 2291-2303. DOI: 10.7544/issn1000-1239.202330451

Citation:

PDF (2334 KB)

Machine Learning Based Runtime Detection and Recovery Method Against UAV Sensor Attacks

School of Cyber Engineering, Xidian University, Xi’an 710071

Funds: This work was supported by the National Natural Science Foundation of China (62272366) and the Key Research and Development Program of Shaanxi Province (2023-YBGY-371).

More Information

Author Bio:
Sun Cong: born in 1982. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software security, program analysis, and unmanned system security

Zeng Huiming: born in 1997. Master, engineer. His main research interest includes unmanned system security

Song Huandong: born in 1997. Master, engineer. His main research interest includes unmanned system security

Wang Yunbo: born in 1995. PhD candidate. His main research interests include UAV security, embedded system, and machine learning

Zhang Zongxu: born in 2001. Master candidate. His main research interest includes unmanned system security

Ma Jianfeng: born in 1963. PhD, professor, PhD supervisor. CCF fellow. His main research interests include information security, cryptography, and network security
Received Date: June 04, 2023
Revised Date: August 10, 2023
Available Online: August 20, 2023

Graphical Abstract

Abstract

Abstract

The sensor attacks towards the flight controller of unmanned aerial vehicle (UAV) induce the UAV to take false sensor signals or data and estimate fault system states, threatening the flight safety of UAVs. The state-of-the-art runtime sensor attack detection and recovery approaches have limited detection accuracy and lacked persistence on the recovery effect. The computational resource limit of the UAV hardware also impacts the accuracy of the detection model and the respective attack detection. We propose a runtime UAV sensor attack detection and recovery approach, called LDR, based on lightweight machine-learning models. We leverage the advantage of the machine-learning model’s representation ability on nonlinear feedback control systems compared with the linear system models to build the machine-learning model for each UAV sensor and predict the system states corresponding to each sensor. We also propose a new attack detection algorithm to mitigate the short-time vibration of the prediction deviation to reduce the potential errors. We apply our approach to detect and recover the GPS sensor attacks and gyroscope attacks. The experimental results show that the performance overhead of our approach meets the flight controller’s real-time requirements. Our approach is highly robust on normal flight tasks, and the prediction model is effective. The comparisons between our approach and related work demonstrate the effectiveness of our approach.
- unmanned aerial vehicle (UAV),
- anomaly detection,
- sensor attack,
- machine learning,
- embedded software

FullText(HTML)

References (31)

References

[1]	王金永,黄志球,杨德艳,等. 面向无人驾驶时空同步约束制导的安全强化学习[J]. 计算机研究与发展,2021,58(12):2585−2603 doi: 10.7544/issn1000-1239.2021.20211023 Wang Jinyong, Huang Zhiqiu, Yang Deyan, et al. Spatio-clock synchronous constraint guided safe reinforcement learning for autonomous driving[J]. Journal of Computer Research and Development, 2021, 58(12): 2585−2603 (in Chinese) doi: 10.7544/issn1000-1239.2021.20211023
[2]	Dash P, Karimibiuki M, Pattabiraman K. Out of control: Stealthy attacks against robotic vehicles protected by control-based techniques [C] //Proc of the 35th Annual Computer Security Applications Conf. New York: ACM, 2019: 660−672
[3]	Lu Xiaozhen, Jie Jingfang, Lin Zihan, et al. Reinforcement learning based energy efficient robot relay for unmanned aerial vehicles against smart jamming[J]. Science China Information Sciences, 2022, 65(1): 112304 doi: 10.1007/s11432-020-3170-2
[4]	Kune D F, Backes J, Clark S S, et al. Ghost talk: mitigating EMI signal injection attacks against analog sensors [C] //Proc of IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2013: 145−159
[5]	Shoukry Y, Martin P, Tabuada P, et al. Non-invasive spoofing attacks for anti-lock braking systems [C] //Proc of 15th Int Workshop on Cryptographic Hardware and Embedded Systems. Berlin: Springer, 2013: 55−72
[6]	Cao Yulong, Xiao Chaowei, Cyr B, et al. Adversarial sensor attack on lidar-based perception in autonomous driving [C] //Proc of the 2019 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2019: 2267−2281
[7]	Schmidt D, Radke K, Camtepe S, et al. A survey and analysis of the GNSS spoofing threat and countermeasures[J]. ACM Computing Surveys, 2016, 48(4): 1−31
[8]	Tu Zhan, Fei Fan, Eagon M, et al. Flight recovery of MAVs with compromised IMU [C] //Proc of IEEE/RSJ Int Conf on Intelligent Robots and Systems. Piscataway, NJ: IEEE, 2019: 3638−3644
[9]	Fei Fan, Tu Zhan, Yu Ruikun, et al. Cross-layer retrofitting of UAVs against cyber-physical attacks [C] //Proc of IEEE Int Conf on Robotics and Automation. Piscataway, NJ: IEEE, 2018: 550−557
[10]	Choi H, Lee W C, Aafer Y, et al. Detecting attacks against robotic vehicles: A control invariant approach [C] //Proc of the 2018 ACM SIGSAC Conf on Comupter and Communications Security. New York: ACM, 2018: 801−816
[11]	Quinonez R, Giraldo J, Salazar L E, et al. SAVIOR: Securing autonomous vehicles with robust physical invariants[C] // Proc of the 29th USENIX Security Symp. Berkeley, CA: USENIX Association, 2020: 895−912
[12]	Choi H, Kate S, Aafer Y, et al. Software-based realtime recovery from sensor attacks on robotic vehicles [C] //Proc of the 23rd Int Symp on Research in Attacks, Intrusions and Defenses. Berkeley, CA: USENIX Association, 2020: 349−364
[13]	Dash P, Li Guanpeng, Chen Zitao, et al. PID-Piper: Recovering robotic vehicles from physical attacks [C] //Proc of the 51st Annual IEEE/IFIP Int Conf on Dependable Systems and Networks. Piscataway, NJ: IEEE, 2021: 26−38
[14]	Nassi B, Bitton R, Masuoka R, et al. SoK: Security and privacy in the age of commercial drones [C] //Proc of IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2021: 1434−1451
[15]	Kwon C, Liu Weiyi, Hwang I. Analysis and design of stealthy cyber attacks on unmanned aerial systems[J]. Journal of Aerospace Information Systems, 2014, 11(8): 525−539 doi: 10.2514/1.I010201
[16]	Kwon C, Yantek S, Hwang I. Real-time safety assessment of unmanned aircraft systems against stealthy cyber attacks[J]. Journal of Aerospace Information Systems, 2016, 13(1): 27−45 doi: 10.2514/1.I010388
[17]	Aboutalebi P, Abbaspour A, Forouzannezhad P, et al. A novel sensor fault detection in an unmanned quadrotor based on adaptive neural observer[J]. Journal of Intelligent and Robotic Systems, 2018, 90: 473−484 doi: 10.1007/s10846-017-0690-7
[18]	Chen Wenxin, Dong Yingfei, Duan Zhenhai, Accurately redirecting a malicious drone [C] //Proc of 19th Annual Consumer Communications and Networking Conf. Piscataway, NJ: IEEE, 2022: 827−834
[19]	Kerns A J, Shepard D P, Bhatti J A, et al. Unmanned aircraft capture and control via GPS spoofing[J]. Journal of Field Robotics, 2014, 31(4): 617−636 doi: 10.1002/rob.21513
[20]	Noh J, Kwon Y, Son Y, et al. Tractor beam: Safe-hijacking of consumer drones with adaptive GPS spoofing [J]. ACM Transactions on Privacy and Security, 2019, 22(2): 12: 1−12: 26
[21]	Son Y, Shin H, Kim D, et al. Rocking drones with intentional sound noise on gyroscopic sensors [C] //Proc of the 24th USENIX Security Symp. Berkeley, CA: USENIX Association, 2015: 881−896
[22]	Trippel T, Weisse O, Xu Wenyuan, et al. WALNUT: Waging doubt on the integrity of MEMS accelerometers with acoustic injection attacks [C] //Proc of IEEE European Symp on Security and Privacy. Piscataway, NJ: IEEE, 2017: 3−18
[23]	Davidson D, Wu Hao, Jellinek R, et al. Controlling UAVs with sensor input spoofing attacks [C] //Proc of the 10th USENIX Workshop on Offensive Technologies. Berkeley, CA: USENIX Association, 2016: 1−11
[24]	Chen Wenxin, Duan Zhenhai, Dong Yingfei. False data injection on EKF-based navigation control [C] //Proc of the Int Conf on Unmanned Aircraft Systems. Piscataway, NJ: IEEE, 2017: 1608−1617
[25]	Xue Nian, Niu Liang, Hong Xianbin, et al. DeepSIM: GPS spoofing detection on UAVs using satellite imagery matching [C] // Proc of the 36th Annual Computer Security Applications Conf. New York: ACM, 2020: 304−319
[26]	Whelan J, Sangarapillai T, Minawi O, et al. Novelty-based intrusion detection of sensor attacks on unmanned aerial vehicles [C] //Proc of the 16th ACM Symp on QoS and Security for Wireless and Mobile Networks. New York: ACM, 2020: 23−28
[27]	Henderson D M. Euler angles, Quaternions, and transformation matrices for space shuttle analysis[R]. NASA STI Repository. 1977 [2023-05-23]. https://ntrs.nasa.gov/citations/19770019231
[28]	Oppenheim A V, Willsky A S, Nawab S H. Signals and Systems [M]. Upper Saddle River, NJ: Prentice Hall, 1997
[29]	Sakoe H, Chiba S. Dynamic programming algorithm optimization for spoken word recognition[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978, 26(1): 43−49 doi: 10.1109/TASSP.1978.1163055
[30]	Tobias Hermann. frugally-deep [EB/OL]. [2023-05-23]. https://github.com/Dobiasd/frugally-deep
[31]	Wang Jinwen, Li Ao, Li Haoran, et al. RT-TEE: Real-time system availability for cyber-physical systems using ARM TrustZone [C] //Proc of IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2022: 352−369

[1]	Wu Jingya, Lu Wenyan, Yan Guihai, Li Xiaowei. HyperTree: High Concurrent B+tree Index Accelerator[J]. Journal of Computer Research and Development, 2023, 60(7): 1661-1677. DOI: 10.7544/issn1000-1239.202111055
[2]	Yang Yongpeng, Jiang Dejun. A Method for Solving the wandering B+ tree Problem[J]. Journal of Computer Research and Development, 2023, 60(3): 539-554. DOI: 10.7544/issn1000-1239.202220555
[3]	Yan Wei, Zhang Xingjun, Ji Zeyu, Dong Xiaoshe, Ji Chenzhao. One-Direction Shift B⁺-Tree Based on Persistent Memory[J]. Journal of Computer Research and Development, 2021, 58(2): 371-383. DOI: 10.7544/issn1000-1239.2021.20200403
[4]	Te Rigen, Li Wei, and Li Xiongfei. Storage Model and Implementation of the Dynamic Ordered Tree[J]. Journal of Computer Research and Development, 2013, 50(5): 969-985.
[5]	Shen Yan, Song Shunlin, Zhu Yuquan. Mining Algorithm of Association Rules Based on Disk Table Resident FP-TREE[J]. Journal of Computer Research and Development, 2012, 49(6): 1313-1322.
[6]	Wang Hongqiang, Li Jianzhong, and Wang Hongzhi. Processing XPath over F&B-Index[J]. Journal of Computer Research and Development, 2010, 47(5): 866-877.
[7]	Zhou Da, Liang Zhichao, Meng Xiaofeng. HF-Tree: An Update-Efficient Index for Flash Memory[J]. Journal of Computer Research and Development, 2010, 47(5): 832-840.
[8]	Sun Xiaojuan, Sun Ninghui, Chen Mingyu. Optimization of B-NIDS for Multicore[J]. Journal of Computer Research and Development, 2007, 44(10): 1733-1740.
[9]	Ju Dapeng, Li Ming, Hu Jinfeng, Wang Dongsheng, Zheng Weimin, and Ma Yongquan. An Algorithm of B\++ Tree Management in P2P Environment[J]. Journal of Computer Research and Development, 2005, 42(8): 1438-1444.
[10]	Dong Daoguo, Liang Liuhong, and Xue Xiangyang. VAR-Tree—A New High-Dimensional Data Index Structure[J]. Journal of Computer Research and Development, 2005, 42(1): 10-17.

Cited By

Cited by

Periodical cited type(1)

1.	LUO Haoran，HU Shuisong，WANG Wenyong，TANG Yuke，ZHOU Junwei. Research on Multi-Core Processor Analysis for WCET Estimation. ZTE Communications. 2024(01): 87-94 .