A comparative evaluation of machine and deep learning models for black hole attack detection in flying ad hoc networks
Imane EL Bahaoui1, Souad Ajjaj2, Hamza Jakha1, Souad EL Houssaini1, Mohammed-Alamine El Houssaini3 and Jamal El Kafi1
Department of Computer Science,Faculty of Sciences, Ibn Tofail University,Kenitra,Morocco2
Higher School of Education and Training,Chouaib Doukkali University,El Jadida,Morocco3
Corresponding Author : Imane EL Bahaoui
Recieved : 09-October-2025; Revised : 14-April-2026; Accepted : 16-April-2026
Abstract
Detecting malicious activities in flying ad hoc networks (FANETs) is critical, as network-layer attacks can disrupt mission-critical communications and compromise fleet security. Machine learning (ML)-based approaches have shown significant potential; however, evaluating their robustness remains challenging due to highly dynamic network topologies and the unique characteristics of aerial communication. The primary objective of this study is to conduct a systematic comparative evaluation of ML models for detecting black hole (BH) routing attacks in ad hoc on-demand distance vector (AODV)-based FANETs. High-fidelity simulation data were generated using Network Simulator 3 (NS-3), incorporating realistic three-dimensional (3D) scenarios with unmanned aerial vehicle (UAV) mobility modeled using the Gauss–Markov algorithm. Three models, random forest (RF), one-dimensional convolutional neural networks (CNNs), and long short-term memory (LSTM) were trained and evaluated using well-defined routing protocol features across varying attacker densities (5%, 10%, and 20%). The evaluation employed a comprehensive, imbalance-aware framework comprising eight performance metrics: accuracy, precision–recall area under the curve (PR-AUC), Matthews correlation coefficient (MCC), precision, recall, F1-score, receiver operating characteristic area under the curve (ROC-AUC), and Cohen’s kappa. The results were validated using rigorous time series cross-validation (TS-CV) and scenario-wise holdout testing. The results demonstrate that LSTM achieved superior performance (98.13% accuracy, 0.896 PR-AUC, 0.835 MCC), followed by RF (96.37%) and CNN (96.31%), with all models enabling early attack detection. Feature analysis revealed interpretable patterns associated with network topology, protocol anomalies, and mobility behavior. These findings establish a transparent and rigorous benchmark for FANET security research, highlighting the effectiveness of early behavioral detection and the importance of comprehensive, imbalance-aware evaluation frameworks for intrusion detection systems (IDS).
Keywords
Flying ad hoc networks (FANETs), Black hole attack detection, Machine learning models, Intrusion detection systems (IDS), NS-3 simulation, UAV communication security.
Cite this article
Bahaoui IE, Ajjaj S, Jakha H, Houssaini SE, Houssaini ME, Kafi JE. A comparative evaluation of machine and deep learning models for black hole attack detection in flying ad hoc networks. International Journal of Advanced Technology and Engineering Exploration. 2026;13(137):566-594. DOI : 10.19101/IJATEE.2025.121221359
[1] Fokkink W, Van GR. Formal methods for mobile ad hoc networks: a survey. Formal Methods in System Design. 2026; 68(1):1-27.
[2] Bhatia TK, Gilhotra S, Bhandari SS, Suden R. Flying ad-hoc networks (FANETs): a review. EAI Endorsed Transactions on Energy Web. 2024; 11:1-7.
[3] Hasan SA, Mohammed MA, Sulaiman SK. Flying ad-hoc networks (FANETs): review of communications, challenges, applications, future direction and open research topics. In ITM web of conferences 2024 (pp. 1-12). EDP Sciences.
[4] Almansor MJ, Din NM, Baharuddin MZ, Ma M, Alsayednoor HM, Al-shareeda MA, et al. Routing protocols strategies for flying ad-hoc network (FANET): review, taxonomy, and open research issues. Alexandria Engineering Journal. 2024; 109:553-77.
[5] Kaur M, Prashar D, Mrsic L, Khan A. Machine learning-based routing protocol in flying. Computers, Materials, & Continua. 2025; 82(2):1615-43.
[6] Zhou L, Yin H, Zhao H, Wei J, Hu D, Leung VC. A comprehensive survey of artificial intelligence applications in UAV-enabled wireless networks. Digital Communications and Networks. 2024.
[7] Atheeq C, Gulzar Z, Al RMS, Alshahrani H, Sulaiman A, Shaikh A. Securing UAV networks: a lightweight chaotic-frequency hopping approach to counter jamming attacks. IEEE Access. 2024; 12:38685-99.
[8] Ceviz O, Sen S, Sadioglu P. A survey of security in uavs and FANETs: issues, threats, analysis of attacks, and solutions. IEEE Communications Surveys & Tutorials. 2024; 27(5):3227-65.
[9] Sarıkaya BS, Bahtiyar Ş. A survey on security of UAV and deep reinforcement learning. Ad Hoc Networks. 2024; 164:103642.
[10] Yapıcıoğlu C, Demirci M, Akcayol MA. Real time malicious drone detection using deep learning on FANETs. In international black sea conference on communications and networking (BlackSeaCom) 2024 (pp. 242-7). IEEE.
[11] Miao S, Pan Q, Zheng D. Unmanned aerial vehicle intrusion detection: deep-meta-heuristic system. Vehicular Communications. 2024; 46:100726.
[12] Hadi HJ, Cao Y, Li S, Hu Y, Wang J, Wang S. Real-time collaborative intrusion detection system in UAV networks using deep learning. IEEE Internet of Things Journal. 2024; 11(20):33371-91.
[13] Alsumayt A, Nagy N, Alsharyofi S, Al IN, Al-rabie R, Alahmadi R, et al. Detecting denial of service attacks (DoS) over the internet of drones (IoD) based on machine learning. Sci. 2024; 6(3):1-19.
[14] Tlili F, Ayed S, Fourati LC. Exhaustive distributed intrusion detection system for UAVs attacks detection and security enforcement (E-DIDS). Computers & Security. 2024; 142:103878.
[15] Alsariera YA, Awwad WF, Algarni AD, Elmannai H, Gamarra M, Escorcia-gutierrez J. Enhanced dwarf mongoose optimization algorithm with deep learning-based attack detection for drones. Alexandria Engineering Journal. 2024; 93:59-66.
[16] Abdelhamid A, Said EM, K AH, A AM. Anomaly-based intrusion detection for blackhole attack mitigation. In proceedings of the 19th international conference on availability, reliability and security 2024 (pp. 1-9). ACM.
[17] Chandrasekar V, Shanmugavalli V, Mahesh TR, Shashikumar R, Borah N, Kumar VV, et al. Secure malicious node detection in flying ad-hoc networks using enhanced AODV algorithm. Scientific Reports. 2024; 14(1):1-16.
[18] Hussain A, Li S, Hussain T, Lin X, Ali F, Alzubi AA. Computing challenges of UAV networks: a comprehensive survey. Computers, Materials & Continua. 2024; 81(2):1-53.
[19] Chandran I, Vipin K. Multi-UAV networks for disaster monitoring: challenges and opportunities from a network perspective. Drone Systems and Applications. 2024; 12:1-28.
[20] Tlili F, Ayed S, Fourati LC. Advancing UAV security with artificial intelligence: a comprehensive survey of techniques and future directions. Internet of Things. 2024; 27:101281.
[21] Örs FK, Levi A. Data driven intrusion detection for 6LoWPAN based IoT systems. Ad Hoc Networks. 2023; 143:103120.
[22] Alashkar TS. Hybrid IDS architecture for IoT security enhancing threat detection with CPBNN and CNN models. International Journal of Advanced Technology and Engineering Exploration. 2024; 11(120):1579-91.
[23] Rutravigneshwaran P, Anitha G. Security model to mitigate black hole attack on internet of battlefield things (IoBT) using trust and K-means clustering algorithm. International Journal of Computer Networks and Applications. 2023; 10(1):1-12.
[24] Santos CL, Mezher AM, León JP, Barrera JC, Guerra EC, Meng J. ML-RPL: machine learning-based routing protocol for wireless smart grid networks. IEEE Access. 2023; 11:57401-14.
[25] Ajjaj S, El HS, Hain M, El HMA. Incremental online machine learning for detecting malicious nodes in vehicular communications using real-time monitoring. Telecom. 2023; 4(3):629-48.
[26] Dhinakaran D, Udhaya SSM, Raja SE, Jasmine JJ. Optimizing mobile ad hoc network routing using biomimicry buzz and a hybrid forest boost regression-ANNs. International Journal of Advanced Computer Science & Applications. 2023; 14(12):92-104.
[27] Jeevaraj D. Feature selection model using naive bayes ML algorithm for WSN intrusion detection system. International Journal of Electrical and Computer Engineering Systems. 2023; 14(2):179-85.
[28] Yıldırım E, Cicioğlu M, Çalhan A. Fog-cloud architecture-driven internet of medical things framework for healthcare monitoring. Medical & Biological Engineering & Computing. 2023; 61(5):1133-47.
[29] Crespo-martínez IS, Campazas-vega A, Guerrero-higueras ÁM, Riego-delcastillo V, Álvarez-aparicio C, Fernández-llamas C. SQL injection attack detection in network flow data. Computers & Security. 2023; 127:1-11.
[30] Wakili A, Bakkali S, Alaoui AE. Machine learning for QoS and security enhancement of RPL in IoT-Enabled wireless sensors. Sensors International. 2024; 5:1-19.
[31] Wijesekara PA, Gunawardena S. A machine learning-aided network contention-aware link lifetime-and delay-based hybrid routing framework for software-defined vehicular networks. Telecom. 2023; 4(3):393-58.
[32] Al SY, Touzene A, Hedjam R. Hybrid deep learning-based intrusion detection system for RPL IoT networks. Journal of Sensor and Actuator Networks. 2023; 12(2):1-25.
[33] Sahay R, Nayyar A, Shrivastava RK, Bilal M, Singh SP, Pack S. Routing attack induced anomaly detection in IoT network using RBM-LSTM. ICT Express. 2024; 10(3):459-64.
[34] Karne RK, Sreeja TK. PMLC-predictions of mobility and transmission in a lane-based cluster VANET validated on machine learning. International Journal on Recent and Innovation Trends in Computing and Communication. 2023; 11:477-83.
[35] Alkanhel R, Khafaga D, El-kenawy ES, Abdelhamid A, Ibrahim A, Amin R, et al. Hybrid grey wolf and dipper throated optimization in network intrusion detection systems. Computers, Materials, & Continua. 2023;74(2):2695-709.
[36] Satyanarayana RK, Selvakumar K. Bi-linear mapping integrated machine learning based authentication routing protocol for improving quality of service in vehicular ad-hoc network. e-Prime-Advances in Electrical Engineering, Electronics and Energy. 2023; 4:1-16.
[37] Ceviz O, Sen S, Sadioglu P. Distributed intrusion detection in dynamic networks of uavs using few-shot federated learning. In international conference on security and privacy in communication systems 2024 (pp. 131-53). Cham: Springer Nature Switzerland.
[38] Nemoto K, Matsutani H. A lightweight reinforcement learning based packet routing method using online sequential learning. IEICE Transactions on Information and Systems. 2023; 106(11):1796-807.
[39] Hemalatha S, Trupthi M, Vaneeta M, Das NN, Krishna RVV, Thangakrishnan MS et al. Comparing watch dog algorithm and classification techniques with machine learning technique to detect the various attackers in mobile adhoc network. Journal of Theoretical and Applied Information Technology. 2024; 102(14):5469-81.
[40] Tan H, Ye T, Rehman S, Rehman O, Tu S, Ahmad J. A novel routing optimization strategy based on reinforcement learning in perception layer networks. Computer Networks. 2023; 237:1-12.
[41] Suresh SS, Prabhu V, Parthasarathy V, Senthilkumar G, Gundu V. Intelligent data routing strategy based on federated deep reinforcement learning for IOT-enabled wireless sensor networks. Measurement: Sensors. 2024; 31:1-9.
[42] Mertens JS, Panebianco A, Surudhi A, Prabagarane N, Galluccio L. Network intelligence vs. jamming in underwater networks: how learning can cope with misbehavior. Frontiers in Communications and Networks. 2023; 4:1-16.
[43] Mahantesh HM, Guptha MN, Hema MS. Energy–QoS-aware data communication and optimal path selection in software-defined networks using EOMBA and IBSO. SN Computer Science. 2023; 4(6):813.
[44] Gupta A, Pavani M, Dargar SK, Dargar A, Chohan AS. Improved extreme learning machine based hunger games search for automatic IP configuration and duplicate node detection. Journal of Communications. 2024;10(3):152-60.
[45] Ceviz O, Sadioglu P, Sen S, Vassilakis VG. A novel federated learning-based IDS for enhancing UAVs privacy and security. Internet of Things. 2025; 31:101592.
[46] Scornet E, Hooker G. Theory of random forests. Annual Review of Statistics and Its Application. 2026; 13(1):99-121.
[47] Li H, Zheng M, Bai F. Artificial intelligence for drug design. Springer Nature Singapore; 2026.
[48] Islam T. Crafting long short-term memory networks. In hands-on deep learning: building models from scratch 2026 (pp. 167-84). Cham: Springer Nature Switzerland.