Attack and anomaly prediction in networks-on-chip of multiprocessor system-on-chip-based IoT utilizing machine learning approaches
Authors: 
Mohammed Sadoon Hathal, Basma Mohammed Saeed, Dina A. Abdulqader, Firas Mahmood MustafaAuthors Info & Claims
Mohammed Sadoon Hathal, Basma Mohammed Saeed, Dina A. Abdulqader, Firas Mahmood MustafaAuthors Info & ClaimsPages 209 - 223
Abstract
The proliferation of multiprocessor system-on-chip (MPSoC) architectures within the Internet of Things (IoT) has introduced notable security challenges. These architectures’ distributed nature, required for smooth communications between the IP cores, opens them up to potential attacks. Among the most significant issues is increased vulnerability to denial-of-service (DoS) attacks in IoT-based MPSoCs, which can influence their functional capabilities and performance. The situation with this vulnerability is further aggravated by the growing tendency to use third-party IPs in MPSoC designs, relying on global supply chains that can provide necessary performance levels as requirements change. This paper addresses the securing network-on-chip (NoC)-based MPSoCs in an IoT environment, targeting their inherent vulnerability due to third-party IP (3PIP) implementation. For timely prediction, in order to prevent potential security risks, particularly DoS attacks, the authors introduce a runtime monitoring mechanism based on ML. The proposed methodology includes the static training of ML models in a smart-placed strategic manner used for runtime attack detection with nominal performance loss. This analysis examines diverse ML models and features in detail, trying to define the use of machine learning for DoS attack identification. The results show considerable differences between the model performances, with XGBoost showing better accuracy, thus implying its potential as a strong solution. Even though the Nive Bayes model shows some degree of reduced accuracy, it implies that a wise selection of models is critical for strengthening the security position in IoT-based MPSoCs.
References
[1]
Özkaya Ö and Örs B Model-based, fully simulated, system-level power consumption estimation of IoT devices Microprocess Microsyst 2024 105 105009
[2]
Muhsen YR, Husin NA, Zolkepli MB, Manshor N, Al-Hchaimi AAJ, and Ridha HM Enhancing NoC-based MPSoC performance: a predictive approach with ANN and guaranteed convergence arithmetic optimization algorithm IEEE Access 2023 11 90143-90157
[3]
Al-Hchaimi AAJ, Sulaiman NB, Mustafa MAB, Mohtar MNB, Hassan SLBM, and Muhsen YR Evaluation approach for efficient countermeasure techniques against denial-of-service attack on MPSoC-based IoT using multi-criteria decision-making IEEE Access 2023 11 89-106
[4]
Al-Hchaimi AAJ, Sulaiman NB, Mustafa MAB, Mohtar MNB, Hassan SLBM, and Muhsen YR A comprehensive evaluation approach for efficient countermeasure techniques against timing side-channel attack on MPSoC-based IoT using multi-criteria decision-making methods Egypt Inform J 2023 24 2 351-364
[5]
Bagga S, Gupta R, and Jose J Modelling and analysis of confluence attack by hardware trojan in NoC Emerg Electron Dev Circuits Syst Select Proc EEDCS Workshop Held Conjunct ISDCS 2022 2023 231-246
[6]
Husin NA, Zolkepli MB, Manshor N, Al-Hchaimi AAJ, and Albahri AS Routing techniques in network-on-chip based multiprocessor-system-on-chip for IOT: a systematic review Iraqi J Comput Sci Math 2024 5 1 181-204
[7]
Surname GN, Surname GN, Surname GN (xxxx) Review of 3D networks-on-chip simulators and plugins. pp 20–23,
[8]
Sankar S, Gupta R, Jose J, and Nandi S TROP: TRust-aware OPportunistic routing in NoC with hardware trojans ACM Trans Des Autom Electron Syst 2024 29 2 1-25
[9]
Kaur SP, Ghose M, Pathak A, and Patole R A survey on mapping and scheduling techniques for 3D Network-on-chip J Syst Archit 2024 10 103064
[10]
Al-Hchaimi AAJ, Flayyih WN, Hashim F, Rusli MS, and Rokhani FZ Review of 3D networks-on-chip simulators and plugins IEEE Asia Pac Conf Postgrad Res Microelectron Electron (PrimeAsia) 2021 2021 17-20
[11]
Wadday AG, Al-hchaimi AAJ, and Ibrahim AJ IOT energy consumption based on PSO-shortest path techniques Recent Adv Electr Electron Eng Formerly Recent Patents Electr Electron Eng 2020 13 7 993-1000
[12]
Biswas AK Using pattern of on-off routers and links and router delays to protect network-on-chip intellectual property ACM Trans Comput Syst 2022
[13]
Daoud L and Rafla N Analysis of black hole router attack in network-on-chip Midwest Symp Circuits Syst 2019 2019 69-72
[14]
Sudusinghe C, Charles S, Mishra P (2021) Denial-of-service attack detection using machine learning in network-on-chip architectures. In: Proc. 2021 15th IEEE/ACM Int. Symp. Networks-on-Chip, NOCS 2021, pp 35–40,
[15]
Reddy BNK and Kumar AS Evaluating the effectiveness of bat optimization in an adaptive and energy-efficient network-on-chip routing framework J Parallel Distrib Comput 2024 5 104853
[16]
Al-Enzi SHZ, Abbas S, Abbood AA, Muhsen YR, Al-Hchaimi AAJ, Almosawi Z (2023) Exploring Research Trends of Metaverse: A Bibliometric Analysis BT - Beyond Reality: Navigating the Power of Metaverse and Its Applications. pp 21–34
[17]
Faccenda RF, Comarú G, Caimi LL, Moraes FG (2023) SeMAP–a method to secure the communication in NoC-based many cores. IEEE Des. Test, 2023
[18]
Deb D and Jose J ZPP: a dynamic technique to eliminate cache pollution in NoC based MPSoCs ACM Trans Embed Comput Syst 2023 22 5s 1-25
[19]
Kumar AS and Naresh Kumar Reddy B An efficient real-time embedded application mapping for NoC based multiprocessor system on chip Wirel Pers Commun 2023 128 4 2937-2952
[20]
Fernandes R, Marcon C, Cataldo R, and Sepulveda J Using smart routing for secure and dependable NoC-Based MPSoCs IEEE/ACM Trans Netw 2020 28 3 1158-1171
[21]
Bhanu PV, Govindan R, Kumar R, Singh V, Soumya J, and Cenkeramaddi LR Fault-tolerant application-specific topology-based NoC and its prototype on an FPGA IEEE Access 2021 9 76759-76779
[22]
Fiorint L, Palermo G, Silvano C (2008) A security monitoring service for NoCs. In: Embed. Syst. Week 2008 - Proc. 6th IEEE/ACM/IFIP Int. Conf. Hardware/Software Codesign Syst. Synth. CODES+ISSS 2008, pp 197–202,
[23]
Wassel HMG et al (2013) SurfNoC: A low latency and provably non-interfering approach to secure networks-on-chip. In: Proc. - Int. Symp. Comput. Archit., pp 583–594,
[24]
JS R, Ancajas DM, Chakraborty K, Roy S (2015) Runtime detection of a bandwidth denial attack from a rogue network-on-chip. In: Proceedings of the 9th International Symposium on Networks-on-Chip, pp 1–8
[25]
Biswas AK, Nandy SK, and Narayan R Router attack toward NoC-enabled MPSoC and monitoring countermeasures against such threat Circuits Syst Signal Process 2015 34 10 3241-3290
[26]
Boraten T, Di Tomaso D, and Kodi AK Secure model checkers for network-on-chip (NoC) architectures Proc ACM Gt Lakes Symp VLSI GLSVLSI 2016 18–20 45-50
[27]
Frey J and Qiaoyan Y A hardened network-on-chip design using runtime hardware Trojan mitigation methods Integration 2017 56 15-31
[28]
Jyv MK, Swain AK, Kumar S, Sahoo SR, and Mahapatra K “Run time mitigation of performance degradation hardware trojan attacks in network on chip IEEE Comput Soc Ann Symp VLSI (ISVLSI) 2018 2018 738-743
[29]
Charles S, Lyu Y, and Mishra P Real-time detection and localization of distributed DoS attacks in NoC-based SoCs IEEE Trans Comput Des Integr Circuits Syst 2020 39 12 4510-4523
[30]
Sinha M, Gupta S, Rout SS, and Deb S Sniffer: a machine learning approach for DoS attack localization in NoC-Based SoCs IEEE J Emerg Sel Top Circuits Syst 2021 11 2 278-291
[31]
Wang H, Halak B (2023) Hardware trojan detection and high-precision localization in NoC-Based MPSoC using machine learning. In: Proceedings of the 28th Asia and South Pacific Design Automation Conference, pp 516–521
[32]
Sudusinghe C, Charles S, Mishra P (2021) Denial-of-service attack detection using machine learning in network-on-chip architectures. In: Proceedings of the 15th IEEE/ACM International Symposium on Networks-on-Chip, pp 35–40
[33]
Yao J, Zhang Y, Mao Z, Li S, Ge M, Chen X (2020) On-line Detection and Localization of DoS Attacks in NoC. In: 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2020, vol. 9, pp 173–178
[34]
Sudusinghe C, Charles S, and Mishra P Network-on-chip attack detection using machine learning Network-on-Chip Security and Privacy 2021 Cham Springer 253-275
[35]
Hu S, Wang H, and Halak B Cascaded machine learning model based DoS attacks detection and classification in NoC IEEE Int Symp Circuits Syst (ISCAS) 2023 2023 1-5
[36]
Abhijitt Dhavlle M, Ahmed M, Mansoor N, Basu K, Ganguly A, and Dinakarrao SMP Defense against on-chip trojans enabling traffic analysis attacks based on machine learning and data augmentation IEEE Trans Comput Aided Des Integr Circuits Syst 2023 42 12 4681-4694
[37]
Kumar M, Kim C, Son Y, Singh SK, and Kim S Empowering cyberattack identification in IoHT networks with neighborhood component-based improvised long short-term memory IEEE Internet Things J 2024
[38]
Karbasi M, Ali M, Bateni SM, Jun C, Jamei M, and Yaseen ZM Boruta extra tree-bidirectional long short-term memory model development for Pan evaporation forecasting: investigation of arid climate condition Alexandria Eng J 2024 86 425-442
[39]
Zhang L and Jánošík D Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches Expert Syst Appl 2024 241 122686
[40]
Elmrabit N, Zhou F, Li F, Zhou H (2020) Evaluation of machine learning algorithms for anomaly detection. In: 2020 international conference on cyber security and protection of digital services (cyber security), 2020, pp 1–8
[41]
Samariya D and Thakkar A A comprehensive survey of anomaly detection algorithms Ann Data Sci 2023 10 3 829-850
[42]
Shanmuganathan V and Suresh A LSTM-Markov based efficient anomaly detection algorithm for IoT environment Appl Soft Comput 2023 136 110054
[43]
Javaheri D, Gorgin S, Lee JA, and Masdari M Fuzzy logic-based DDoS attacks and network traffic anomaly detection methods: classification, overview, and future perspectives Inform Sci 2023 626 315-338
[44]
Chaves CG, Azad SP, Hollstein T, and Sepúlveda J DoS attack detection and path collision localization in NoC-based MpsoC architectures J Low Power Electron Appl 2019 9 1 1-20
[45]
Chaves CG, Azad SP, Hollstein T, Sepúlveda J (2018) A distributed DoS detection scheme for NoC-based MPSoCs. In: 2018 IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC), pp 1–6
Index Terms
- Attack and anomaly prediction in networks-on-chip of multiprocessor system-on-chip-based IoT utilizing machine learning approaches
Index terms have been assigned to the content through auto-classification.
Recommendations
Design and implementation of Denial-of-Service attack in network of multiprocessor systems-on-chip with anomaly detection approach
AbstractIoT architecture based on the multiprocessor system-on-chip (MPSoC) is widely used because of the third-party intellectual property cores (3PIPs) supplied globally. Therefore, 3PIPs present an intrinsic security risk. Decentralization of the ...
An asynchronous hierarchical router for networks-on-chip-based three-dimensional multi-processor system-on-chip
Three-dimensional networks-on-chip (3D NoC) are rising as a good approach to well managed complex interconnections in 3D multi-processor system-on-chip (MPSoC). This paper introduces a new router in order to enhance throughput and latency compared to ...
Embedded Security Accelerators within Network-on-Chip Environments
HEART '24: Proceedings of the 14th International Symposium on Highly Efficient Accelerators and Reconfigurable TechnologiesThe adoption of Network-on-Chip (NoC) as the backbone for Multiprocessor System-on-Chip (MPSoC) communications is becoming increasingly common due to its scalability. Nevertheless, the vulnerability of these systems to security exploits, particularly ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 08 May 2024
Accepted: 23 March 2024
Revision received: 04 March 2024
Received: 28 January 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Jan 2025