Trustworthy Artificial Intelligence Methods for Users’ Physical and Environmental Security: A Comprehensive Review
Source abstract
Abstract
Artificial Intelligence is an indispensable element of the modern world, constantly evolving and contributing to the emergence of new technologies. We meet it in everyday applications, primarily using intelligent systems that aim to improve our lives. Artificial Intelligence techniques must inspire users’ trust because they significantly impact virtually every industry and person. For this reason, systems using Artificial Intelligence are subject to many requirements to verify their trustworthiness in various aspects. This review focused on users’ physical and environmental security, considering the safety and robustness dimensions of Trustworthy Artificial Intelligence. We examined these Trustworthy Artificial Intelligence solutions and dimensions because security is one of the most-critical aspects of human life and can be considered in many different contexts. We examined the trustworthiness of Artificial Intelligence techniques in systems supporting road safety and securing computer network users. Also, we analyzed the challenges and requirements of the newly designed solutions using Trustworthy Artificial Intelligence methods. Verifying Trustworthy Artificial Intelligence solutions and their practical use will increase users’ physical and environmental security.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Traffic Prediction and Management Techniques · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Częstochowa University of Technology, 42-201 Czestochowa, Poland
References (100+)
Show source-provided references
1. Liu, J., Tang, Y., Zhao, H., Wang, X., Li, F., and Zhang, J. (2023). CPS Attack Detection under Limited Local Information in Cyber Security: An Ensemble Multi-node Multi-class Classification Approach. ACM Trans. Sens. Netw.10.1145/3585520 ↗
2. Trustworthy artificial intelligence10.1007/s12525-020-00441-4 ↗
3. Trustworthy Artificial Intelligence: A Review10.1145/3491209 ↗
4. Review on cyber-physical and cyber-security system in smart grid: Standards, protocols, constraints, and recommendations10.1016/j.jnca.2022.103540 ↗
5. Automated Analysis of Blood Smear Images for Leukemia Detection: A Comprehensive Review10.1145/3514495 ↗
6. Alzamer, H., Abuhmed, T., and Hamad, K. (2021). A short review on the Machine Learning-guided oxygen uptake prediction for sport science applications. Electronics, 10.10.3390/electronics10161956 ↗
7. A Survey on Voice Assistant Security: Attacks and Countermeasures10.1145/3527153 ↗
8. Raut, R., Jadhav, A., Jaiswal, S., and Pathak, P. (2022). Intelligent Systems for Rehabilitation Engineering, John Wiley & Sons.10.1002/9781119785651 ↗
9. Kubanek, M., and Bobulski, J. (2018). Device for Acoustic Support of Orientation in the Surroundings for Blind People. Sensors, 18.10.3390/s18124309 ↗
10. Nait Aicha, A., Englebienne, G., Van Schooten, K.S., Pijnappels, M., and Kröse, B. (2018). Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry. Sensors, 18.10.3390/s18051654 ↗
11. Platt, F. (2012). Computer Security Handbook, John Wiley & Sons.
12. Amelia—A new security protocol for protection against false links10.1016/j.comcom.2021.07.030 ↗
13. Guembe, B., Azeta, A., Misra, S., and Ahuja, R. (2022, January 4–7). Trustworthy Machine Learning Approaches for Cyberattack Detection: A Review. Proceedings of the International Conference on Computational Science and Its Applications, Malaga, Spain.10.1007/978-3-031-10548-7_20 ↗
14. The EU Approach to Ethics Guidelines for Trustworthy Artificial Intelligence10.9785/cri-2019-200402 ↗
15. Trustworthy AI and corporate governance: The EU’s ethics guidelines for trustworthy artificial intelligence from a company law perspective10.1007/s40804-021-00224-0 ↗
16. Trustworthy AI: A Computational Perspective
17. Pedestrian safety using the Internet of Things and sensors: Issues, challenges, and open problems10.1016/j.future.2022.03.036 ↗
18. Artificial Intelligence in Transportation Systems A Critical Review10.47672/ajce.1487 ↗
19. Bhattacharya, S., Jha, H., and Nanda, R.P. (2021, January 26–28). Application of IoT and Artificial Intelligence in Road Safety. Proceedings of the 2022 Interdisciplinary Research in Technology and Management (IRTM), Kolkata, India.10.1109/IRTM54583.2022.9791529 ↗
20. Olugbade, S., Ojo, S., Imoize, A.L., Isabona, J., and Alaba, M.O. (2022). A Review of Artificial Intelligence and Machine Learning for Incident Detectors in Road Transport Systems. Math. Comput. Appl., 27.10.3390/mca27050077 ↗
21. Survey on artificial intelligence (AI) techniques for vehicular ad-hoc networks (VANETs)
22. Abdullahi, M., Baashar, Y., Alhussian, H., Alwadain, A., Aziz, N., Capretz, L.F., and Abdulkadir, S.J. (2022). Detecting cybersecurity attacks in internet of things using artificial intelligence methods: A systematic literature review. Electronics, 11.10.3390/electronics11020198 ↗
23. Intrusion detection and prevention in fog based IoT environments: A systematic literature review10.1016/j.comnet.2022.109154 ↗
24. Zero-day attack detection: A systematic literature review10.1007/s10462-023-10437-z ↗
25. IoT malware: An attribute-based taxonomy, detection mechanisms and challenges10.1007/s12083-023-01478-w ↗
26. A systematic analysis of deep learning methods and potential attacks in internet-of-things surfaces10.1007/s00521-023-08634-6 ↗
27. A Review of Deep Machine Learning10.4028/www.scientific.net/JERA.24.124 ↗
28. Face recognition using deep learning methods a review10.14419/ijet.v7i4.22375 ↗
29. Contreras-Valenzuela, M.R., Seuret-Jiménez, D., Hdz-Jasso, A.M., León Hernández, V.A., Abundes-Recilla, A.N., and Trutié-Carrero, E. (2022). Design of a Fuzzy Logic Evaluation to Determine the Ergonomic Risk Level of Manual Material Handling Tasks. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19116511 ↗
30. Serrano, W. (2018). Neural networks in big data and Web search. Data, 4.10.3390/data4010007 ↗
31. Senthilkumar, M., and Chowdhary, C.L. (2019). Intelligent Systems, Apple Academic Press.
32. Completely quantum neural networks10.1103/PhysRevA.106.022601 ↗
33. Agavanakis, K.N., Karpetas, G.E., Taylor, M., Pappa, E., Michail, C.M., Filos, J., Trachana, V., and Kontopoulou, L. (2019, January 10–12). Practical Machine Learning based on cloud computing resources. Proceedings of the AIP Conference Proceedings, Beirut, Lebanon.10.1063/1.5117023 ↗
34. Tutorial: Neuromorphic spiking neural networks for temporal learning10.1063/1.5042243 ↗
35. Schuman, C.D., Potok, T.E., Patton, R.M., Birdwell, J.D., Dean, M.E., Rose, G.S., and Plank, J.S. (2017). A Survey of Neuromorphic Computing and Neural Networks in Hardware. arXiv.
36. Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook10.1109/JPROC.2021.3067593 ↗
37. Orchard, G., Frady, E.P., Rubin, D.B.D., Sanborn, S., Shrestha, S.B., Sommer, F.T., and Davies, M. (2021, January 20–22). Efficient neuromorphic signal processing with loihi 2. Proceedings of the 2021 IEEE Workshop on Signal Processing Systems (SiPS), Coimbra, Portugal.10.1109/SiPS52927.2021.00053 ↗
38. Cachi, P.G., Ventura, S., and Cios, K.J. (2022). MT-SNN: Spiking Neural Network that Enables Single-Tasking of Multiple Tasks. arXiv.
39. Nengo: A Python tool for building large-scale functional brain models10.3389/fninf.2013.00048 ↗
40. Neural algorithms and computing beyond Moore’s law10.1145/3231589 ↗
41. Training Spiking Neural Networks Using Lessons From Deep Learning10.1109/JPROC.2023.3308088 ↗
42. SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks With at Most One Spike per Neuron10.3389/fnins.2019.00625 ↗
43. Simulation Neurotechnologies for Advancing Brain Research: Parallelizing Large Networks in NEURON10.1162/NECO_a_00876 ↗
44. Fast Simulation of a Multi-Area Spiking Network Model of Macaque Cortex on an MPI-GPU Cluster10.3389/fninf.2022.883333 ↗
45. Brian 2, an intuitive and efficient neural simulator10.7554/eLife.47314 ↗
46. Niedermeier, L., Chen, K., Xing, J., Das, A., Kopsick, J., Scott, E., Sutton, N., Weber, K., Dutt, N., and Krichmar, J.L. (2022, January 18–23). CARLsim 6: An Open Source Library for Large-Scale, Biologically Detailed Spiking Neural Network Simulation. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy.10.1109/IJCNN55064.2022.9892644 ↗
47. N2A: A computational tool for modeling from neurons to algorithms10.3389/fncir.2014.00001 ↗
48. Gerstner, W., Kistler, W.M., and Naud, R. (2014). Neuronal Dynamics, Cambridge University Press.10.1017/CBO9781107447615 ↗
49. Brain-inspired learning on neuromorphic substrates10.1109/JPROC.2020.3045625 ↗
50. Hebbian learning and spiking neurons10.1103/PhysRevE.59.4498 ↗
51. (2023, June 12). The 6 Levels of Vehicle Autonomy Explained. Available online: https://www.synopsys.com/automotive/autonomous-driving-levels.html.
52. Machine Learning applied to road safety modeling: A systematic literature review
53. Understanding the potential of emerging digital technologies for improving road safety10.1016/j.aap.2021.106543 ↗
54. Road vehicle recognition algorithm in safety assistant driving based on artificial intelligence10.1007/s00500-021-06011-w ↗
55. A Survey of Driving Safety With Sensing, Vehicular Communications, and Artificial Intelligence-Based Collision Avoidance10.1109/TITS.2021.3083927 ↗
56. Artificial Intelligence for Vehicle Behavior Anticipation: Hybrid Approach Based on Maneuver Classification and Trajectory Prediction10.1109/ACCESS.2020.2982170 ↗
57. Accident Risk Prediction and Avoidance in Intelligent Semi-autonomous Vehicles Based on Road Safety Data and Driver Biological Behaviours10.3233/JIFS-191375 ↗
58. Pedestrian safety at signalized intersections: Spatial and machine learning approaches10.1016/j.jth.2021.101322 ↗
59. (2023, June 01). Police Report 2021. Available online: https://statystyka.policja.pl/download/20/381967/Wypadkidrogowe2021.pdf.
60. A Review of Intelligent Driving Pedestrian Detection Based on Deep Learning10.1155/2021/5410049 ↗
61. Szarvas, M., Yoshizawa, A., Yamamoto, M., and Ogata, J. (2005, January 6–8). Pedestrian detection with convolutional neural networks. Proceedings of the IEEE Proceedings. Intelligent Vehicles Symposium, Las Vegas, NV, USA.10.1109/IVS.2005.1505106 ↗
62. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
63. (2023, September 20). R-CNN, Fast R-CNN, Faster R-CNN, YOLO—Object Detection Algorithms. Available online: https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e.
64. Dong, P., and Wang, W. (2016, January 27–30). Better region proposals for pedestrian detection with R-CNN. Proceedings of the 2016 Visual Communications and Image Processing (VCIP), Chengdu, China.10.1109/VCIP.2016.7805452 ↗
65. Fast Feature Pyramids for Object Detection10.1109/TPAMI.2014.2300479 ↗
66. Pedestrian and cyclist detection based on deep neural network fast R-CNN10.1177/1729881419829651 ↗
67. Huang, D.S., Bevilacqua, V., Premaratne, P., and Gupta, P. (2017, January 7–10). Pedestrian Detection Based on Fast R-CNN and Batch Normalization. Proceedings of the Intelligent Computing Theories and Application, Liverpool, UK.10.1007/978-3-319-63309-1 ↗
68. Scale-Aware Fast R-CNN for Pedestrian Detection
69. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv.
70. Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016, January 11–14). Is Faster R-CNN Doing Well for Pedestrian Detection?. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands.10.1007/978-3-319-46466-4 ↗
71. Zhang, H., Du, Y., Ning, S., Zhang, Y., Yang, S., and Du, C. (2017, January 15–18). Pedestrian Detection Method Based on Faster R-CNN. Proceedings of the 2017 13th International Conference on Computational Intelligence and Security (CIS), Hong Kong, China.10.1109/CIS.2017.00099 ↗
72. Hung, G.L., Sahimi, M.S.B., Samma, H., Almohamad, T.A., and Lahasan, B. (2020). Faster R-CNN Deep Learning Model for Pedestrian Detection from Drone Images, Springer.10.1007/s42979-020-00125-y ↗
73. An Improved Faster R-CNN Pedestrian Detection Algorithm Based on Feature Fusion and Context Analysis10.1109/ACCESS.2020.3012558 ↗
74. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
75. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
76. InceptionDepth-wiseYOLOv2: Improved implementation of YOLO framework for pedestrian detection10.1007/s13735-022-00239-4 ↗
77. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
78. Li, A., Gao, X., and Qu, C. (2021). Intelligent Life System Modelling, Image Processing and Analysis, Proceedings of the 7th International Conference on Life System Modeling and Simulation, LSMS 2021 and 7th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2021, Hangzhou, China, 30 October–1 November 2021, Springer.
79. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
80. Wen, B., and Wu, M. (2020, January 11–14). Study on Pedestrian Detection Based on an Improved YOLOv4 Algorithm. Proceedings of the 2020 IEEE 6th International Conference on Computer and Communications (ICCC), Chengdu, China.
81. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2023, September 20). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, Available online: http://xxx.lanl.gov/abs/1704.04861.
82. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). Computer Vision—ECCV 2016, Springer International Publishing.
83. Optimized MobileNet + SSD: A real-time pedestrian detection on a low-end edge device10.1007/s13735-021-00212-7 ↗
84. El-Sayed, S.A., Spyrou, T., Pavlidis, A., Afacan, E., Camuñas-Mesa, L.A., Linares-Barranco, B., and Stratigopoulos, H.G. (2020, January 13–15). Spiking Neuron Hardware-Level Fault Modeling. Proceedings of the 2020 IEEE 26th International Symposium on On-Line Testing and Robust System Design (IOLTS), Napoli, Italy.10.1109/IOLTS50870.2020.9159745 ↗
85. Spyrou, T., El-Sayed, S.A., Afacan, E., Camunas-Mesa, L.A., Linares-Barranco, B., and Stratigopoulos, H.G. (2021, January 1–5). Neuron Fault Tolerance in Spiking Neural Networks. Proceedings of the 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Virtual.10.23919/DATE51398.2021.9474081 ↗
86. Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades10.3389/fnins.2015.00437 ↗
87. Amir, A., Taba, B., Berg, D., Melano, T., McKinstry, J., Di Nolfo, C., Nayak, T., Andreopoulos, A., Garreau, G., and Mendoza, M. (2017, January 21–26). A Low Power, Fully Event-Based Gesture Recognition System. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.781 ↗
88. Spyrou, T., El-Sayed, S.A., Afacan, E., Camuñas-Mesa, L.A., Linares-Barranco, B., and Stratigopoulos, H.G. (2022, January 25–27). Reliability Analysis of a Spiking Neural Network Hardware Accelerator. Proceedings of the 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Valencia, Spain.10.23919/DATE54114.2022.9774711 ↗
89. Chen, L., Kapoor, S., and Bhatia, R. (2014). Intelligent Systems for Science and Information: Extended and Selected Results from the Science and Information Conference 2013, Springer International Publishing.10.1007/978-3-319-04702-7 ↗
90. Han, W.S., and Han, I.S. (2015, January 28–30). Neuromorphic visual object detection for enhanced driving safety. Proceedings of the 2015 Science and Information Conference (SAI), London, UK.10.1109/SAI.2015.7237222 ↗
91. Prez, H., Rudomin, I., and Tabarez-Paz, I. (2016). Support Vector Machine and Spiking Neural Networks for Data Driven Prediction of Crowd Character Movement, MIT Press.
92. Ramanishka, V., Chen, Y.T., Misu, T., and Saenko, K. (2018, January 18–23). Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00803 ↗
93. Gaurav, R. (2022). Driving Scene Understanding Using Spiking Neural Networks. [Master’s Thesis, University of Waterloo].
94. A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents10.3389/fnins.2022.753900 ↗
95. Reinforcement Learning with Modulated Spike Timing–Dependent Synaptic Plasticity10.1152/jn.00364.2007 ↗
96. Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules
97. Nguyen, E. (2021). Temporal Spike Attribution: A Local Feature-Based Explanation for Temporally Coded Spiking Neural Networks. [Master’s Thesis, University of Twente].
98. Visual explanations from spiking neural networks using inter-spike intervals10.1038/s41598-021-98448-0 ↗
99. Seras, A.M., Ser, J.D., Lobo, J.L., Garcia-Bringas, P., and Kasabov, N. (2022). A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks. arXiv.
100. Event-Based Vision: A Survey10.1109/TPAMI.2020.3008413 ↗