pith. sign in

arxiv: 2606.17119 · v1 · pith:XXRTEG46new · submitted 2026-06-15 · 💻 cs.CR · cs.AI

Graph neural networks at war: integrating cybersecurity and drone intelligence in the Israeli-Iranian conflict

Sozan Sulaiman Maghdid , Tarik Ahmed Rashid , Shavan Askar This is my paper

Pith reviewed 2026-06-27 03:27 UTC · model grok-4.3

classification 💻 cs.CR cs.AI
keywords graph neural networkscybersecuritydronesUAVintrusion detectioncyber-physical systemsGraphSAGEswarm coordination
0
0 comments X

The pith

Graph neural networks detect cyber intrusions on drones and enable coordinated responses in physical cyber systems.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper examines the use of Graph Neural Networks to integrate cybersecurity and drone management in systems facing both cyber attacks and unmanned aerial vehicles. It proposes a procedure where these networks learn network structures to spot malicious activity and guide drone actions. An emulation case study demonstrates that this approach supports situational awareness, swarm coordination, and adaptive maneuvers. Performance metrics include a 94.2 percent detection rate, 0.955 area under the ROC curve, and 1.4 seconds average response time, with GraphSAGE outperforming other graph networks.

Core claim

The central discovery is that graph-based learning can assist with the situational awareness, swarm coordination, and adaptive maneuver in response to cyberattacks on drones. Based on an emulation-based case study creating cyberattacks models to provoke drone responses, the method achieves a detection rate of 94.2, average area under the receiver operating characteristic of 0.955 and an average response time of 1.4 seconds. Comparative experiments show the proposed GraphSAGE network is more effective than Graphical Convolutional Networks and Graphical Attention Networks.

What carries the argument

Graph Neural Networks, specifically GraphSAGE, applied to model the interactions between cyber intrusions and UAV responses for intrusion detection and drone coordination.

If this is right

  • Graph-based learning assists with situational awareness, swarm coordination, and adaptive maneuver.
  • This method achieves a 94.2% detection rate, 0.955 AUC, and 1.4 seconds response time.
  • GraphSAGE outperforms GCNs and GATs in the same cyber-physical scenario.
  • Graphical neural networks can avert intrusion and support responses in dynamic cyber-physical systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the emulation reflects real conditions, similar GNN models could improve defense in other drone swarm operations against cyber threats.
  • Extending this to physical hardware tests would confirm if the metrics hold outside simulation.
  • Integrating GNNs this way might reduce response times further by combining detection directly with maneuver planning.

Load-bearing premise

The emulation-based case study accurately captures the dynamics of real cyberattacks and UAV responses allowing the performance metrics to apply beyond the simulation.

What would settle it

Running the same cyberattacks on actual physical drones and observing detection rates significantly below 94% or response times much longer than 1.4 seconds would challenge the claim.

read the original abstract

Physical cyber systems have brought about new threats and challenges in detection and immediate response. This study examines how Graph Neural Networks (GNNs) can be used to aid cybersecurity and drone management in a physical cyber system comprising of cyber intrusions and unmanned aerial vehicles (UAVs). By providing a bridge between structural understanding of graphical neural networks, this work has provided an integrated procedure that allows intrusion detection systems to educate on underlying network structures, identify malicious activity, and facilitates drone response measures. Based on an emulation-based case study, cyberattacks models were created to provoke the responses of the drones, which proved that graph-based learning can assist with the situational awareness, swarm coordination, and adaptive maneuver. According to the performance valuation, this method has a detection rate of 94.2, average area under the receiver operating characteristic (ROC) of 0.955 and an average response time of 1.4 seconds. Comparative experiments reveal that proposed GraphSAGE network is more effective than the Graphical Convolutional Networks (GCNs) and Graphical Attention Networks (GATs) in the identical situation. Such findings prove that graphical neural networks can be used to avert intrusion and response of dynamic cyber-physical systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper claims that Graph Neural Networks (GNNs), particularly GraphSAGE, can integrate cybersecurity and drone intelligence in physical cyber systems by enabling intrusion detection, situational awareness, swarm coordination, and adaptive UAV maneuvers. An emulation-based case study models cyberattacks to provoke drone responses and reports performance of 94.2% detection rate, 0.955 average AUC, and 1.4 s average response time, with GraphSAGE outperforming GCN and GAT.

Significance. If the emulation were shown to faithfully reproduce real cyber-physical UAV attack surfaces, communication graphs, kinematics, and latencies, the work could demonstrate a practical role for GNNs in real-time defense of drone swarms. The absence of any methodological detail, external validation, or statistical analysis means the reported metrics cannot currently be evaluated or generalized.

major comments (2)
  1. [Abstract] Abstract: the performance metrics (94.2% detection rate, 0.955 AUC, 1.4 s response time) are presented with no information on dataset construction, training procedure, baseline comparisons, error bars, or statistical significance, so the numbers cannot be assessed against the claim that GraphSAGE is more effective.
  2. [Abstract] Abstract / Case-study description: the emulation is asserted to 'prove' that graph-based learning assists situational awareness and adaptive maneuver, yet no description is given of the attack models, communication-graph construction, UAV dynamics, or any sensitivity analysis on emulation parameters; without this, the central generalization to physical cyber systems cannot be evaluated.
minor comments (2)
  1. [Abstract] Abstract: 'performance valuation' should read 'performance evaluation'; 'Graphical Convolutional Networks' and 'Graphical Attention Networks' should be 'Graph Convolutional Networks' and 'Graph Attention Networks'.
  2. [Title] The title references the Israeli-Iranian conflict, but the manuscript supplies only a generic emulation with no incident data, topology, or scenario drawn from that conflict.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. We agree that the current version of the manuscript lacks sufficient methodological transparency, which limits the ability to evaluate the reported results and claims. We will revise the paper to include expanded descriptions of the experimental setup, models, and analysis to address these concerns.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the performance metrics (94.2% detection rate, 0.955 AUC, 1.4 s response time) are presented with no information on dataset construction, training procedure, baseline comparisons, error bars, or statistical significance, so the numbers cannot be assessed against the claim that GraphSAGE is more effective.

    Authors: We agree that the abstract and current manuscript do not provide these details. In the revision we will add a Methods section describing dataset construction (synthetic cyberattack scenarios generated in the emulation), the supervised training procedure for the GNNs, the exact baseline implementations of GCN and GAT under matched conditions, error bars from repeated runs, and statistical significance tests (e.g., Wilcoxon signed-rank tests) to support the comparative claims. revision: yes

  2. Referee: [Abstract] Abstract / Case-study description: the emulation is asserted to 'prove' that graph-based learning assists situational awareness and adaptive maneuver, yet no description is given of the attack models, communication-graph construction, UAV dynamics, or any sensitivity analysis on emulation parameters; without this, the central generalization to physical cyber systems cannot be evaluated.

    Authors: We acknowledge that the manuscript provides insufficient detail on the emulation. The revised version will include explicit descriptions of the attack models (e.g., specific intrusion types targeting communication links), the construction of the dynamic communication graph from UAV positions and connectivity, the kinematic and dynamic models used for UAV motion, and sensitivity analyses varying key parameters such as latency, packet loss, and swarm density to evaluate robustness of the reported outcomes. revision: yes

Circularity Check

0 steps flagged

No derivation chain or self-referential steps present in the empirical case study.

full rationale

The manuscript reports performance metrics (94.2% detection rate, AUC 0.955, 1.4 s response time) and a comparative ranking of GraphSAGE over GCN/GAT directly from an emulation-based case study. No equations, parameter-fitting procedures, uniqueness theorems, or self-citations appear in the provided text that would reduce any claimed result to its own inputs by construction. The central claims rest on experimental outputs rather than a mathematical derivation chain, so none of the enumerated circularity patterns apply.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit free parameters, axioms, or invented entities; all such elements remain unknown.

pith-pipeline@v0.9.1-grok · 5751 in / 1159 out tokens · 56134 ms · 2026-06-27T03:27:31.509488+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

60 extracted references · 42 canonical work pages

  1. [1]

    Traditional battlefields have moved pipeline for the cyber-drone telemetry dataset

    Introduction The landscape of modern warfare is undergoing a radical transformation. Traditional battlefields have moved pipeline for the cyber-drone telemetry dataset. Figure 5. Data loading and preprocessing pipeline for the cyber-drone telemetry dataset 5.3 Dataset Preprocessing Before creating a graph neural network (GNN) model using the drone telemet...

  2. [2]

    Applied Artificial Intelligence in Modern Warfare & National Security Policy,

    B. S. Haney, “Applied Artificial Intelligence in Modern Warfare & National Security Policy,” SSRN Electron J, 2019, doi: 10.2139/ssrn.3454204

    work page doi:10.2139/ssrn.3454204 2019

  3. [3]

    Autonomous Vehicles and Intelligent Automation: Applications, Challenges, and Opportunities,

    G. Bathla et al., “Autonomous Vehicles and Intelligent Automation: Applications, Challenges, and Opportunities,” 2022. doi: 10.1155/2022/7632892

    work page doi:10.1155/2022/7632892 2022

  4. [4]

    Image objects and geographic objects,

    R. Salama, F. Al-Turjman, and R. Culmone, “AI-Powered Drone to Address Smart City Security Issues,” in Lecture Notes in Networks and Systems, 2023. doi: 10.1007/978-3- 031-28694-0_27

    work page doi:10.1007/978-3- 2023

  5. [5]

    Algorithms at war: The promise, peril, and limits of artificial intelligence,

    B. M. JENSEN, C. WHYTE, and S. CUOMO, “Algorithms at war: The promise, peril, and limits of artificial intelligence,” Int Stud Rev, vol. 22, no. 3, 2020, doi: 10.1093/isr/viz025

    work page doi:10.1093/isr/viz025 2020

  6. [6]

    A survey on artificial intelligence techniques for security event correlation: models, challenges, and opportunities,

    D. Levshun and I. Kotenko, “A survey on artificial intelligence techniques for security event correlation: models, challenges, and opportunities,” Artif Intell Rev, vol. 56, no. 8, 2023, doi: 10.1007/s10462-022-10381-4

    work page doi:10.1007/s10462-022-10381-4 2023

  7. [7]

    Investigating the applications of artificial intelligence in cyber security,

    N. N. Abbas, T. Ahmed, S. H. U. Shah, M. Omar, and H. W. Park, “Investigating the applications of artificial intelligence in cyber security,” Scientometrics, vol. 121, no. 2, 2019, doi: 10.1007/s11192-019-03222-9

    work page doi:10.1007/s11192-019-03222-9 2019

  8. [8]

    Developments in Artificial Intelligence and Opportunities and Challenges for Military Modeling and Simulation,

    A. J. Fawkes, “Developments in Artificial Intelligence and Opportunities and Challenges for Military Modeling and Simulation,” Proc 2017 NATO M&S Symp, 2017

    2017

  9. [9]

    The AI-cyber nexus: implications for military escalation, deterrence and strategic stability,

    J. Johnson, “The AI-cyber nexus: implications for military escalation, deterrence and strategic stability,” J Cyber Policy, vol. 4, no. 3, 2019, doi: 10.1080/23738871.2019.1701693

    work page doi:10.1080/23738871.2019.1701693 2019

  10. [10]

    Artificial intelligence & future warfare: Implications for international security,

    J. Johnson, “Artificial intelligence & future warfare: Implications for international security,” Def Secur Anal, vol. 35, no. 2, 2019, doi: 10.1080/14751798.2019.1600800

    work page doi:10.1080/14751798.2019.1600800 2019

  11. [11]

    InProceedings of the 15th ACM SIGPLAN-SIGACT symposium on Principles of programming languages

    A. Platzer, Logical foundations of cyber-physical systems. 2018. doi: 10.1007/978-3-319- 63588-0

    work page doi:10.1007/978-3-319- 2018

  12. [12]

    Graph neural networks: Historical backgrounds, present revolutions, and conventionalization for the future,

    S. S. Maghdid, T. A. Rashid, and S. K. Askar, “Graph neural networks: Historical backgrounds, present revolutions, and conventionalization for the future,” Int J Data Sci Anal, 2025, doi: 10.1007/s41060-025-00797-w

    work page doi:10.1007/s41060-025-00797-w 2025

  13. [13]

    Advancing Cybersecurity: Graph Neural Networks in Threat Intelligence Knowledge Graphs,

    L. Li, F. Qiang, and L. Ma, “Advancing Cybersecurity: Graph Neural Networks in Threat Intelligence Knowledge Graphs,” ACM Int Conf Proceeding Ser, pp. 737–741, 2024, doi: 10.1145/3677182.3677314

    work page doi:10.1145/3677182.3677314 2024

  14. [14]

    Design Challenges of Multi-UAV Systems in Cyber-Physical Applications: A Comprehensive Survey and Future Directions,

    R. Shakeri et al., “Design Challenges of Multi-UAV Systems in Cyber-Physical Applications: A Comprehensive Survey and Future Directions,” IEEE Commun Surv Tutorials, vol. 21, no. 4, pp. 3340–3385, 2019, doi: 10.1109/COMST.2019.2924143

    work page doi:10.1109/comst.2019.2924143 2019

  15. [15]

    Low-Altitude Unmanned Aerial Vehicles- Based Internet of Things Services: Comprehensive Survey and Future Perspectives,

    N. Hossein Motlagh, T. Taleb, and O. Arouk, “Low-Altitude Unmanned Aerial Vehicles- Based Internet of Things Services: Comprehensive Survey and Future Perspectives,”

  16. [16]

    doi: 10.1109/JIOT.2016.2612119

    work page doi:10.1109/jiot.2016.2612119 2016

  17. [17]

    Deep Neural Networks for Spatial-Temporal Cyber-Physical Systems: A Survey,

    A. A. Musa, A. Hussaini, W. Liao, F. Liang, and W. Yu, “Deep Neural Networks for Spatial-Temporal Cyber-Physical Systems: A Survey,” Futur Internet, vol. 15, no. 6, pp. 1–24, 2023, doi: 10.3390/fi15060199

    work page doi:10.3390/fi15060199 2023

  18. [18]

    Simulation and Machine Learning in Beyond Visual Range Air Combat: A Survey,

    A. N. Costa, J. P. A. Dantas, E. Scukins, F. L. L. Medeiros, and P. A-Gren, “Simulation and Machine Learning in Beyond Visual Range Air Combat: A Survey,” IEEE Access, no. April, pp. 76755–76774, 2025, doi: 10.1109/ACCESS.2025.3563811

    work page doi:10.1109/access.2025.3563811 2025

  19. [19]

    Graph neural networks embedded with domain knowledge for cyber threat intelligence entity and relationship mining,

    G. Liu, K. Lu, and S. Pi, “Graph neural networks embedded with domain knowledge for cyber threat intelligence entity and relationship mining,” PeerJ Comput Sci, vol. 11, pp. 1–27, 2025, doi: 10.7717/peerj-cs.2769

    work page doi:10.7717/peerj-cs.2769 2025

  20. [20]

    Survey on Unmanned Aerial Vehicle Networks: A Cyber Physical System Perspective,

    H. Wang, H. Zhao, J. Zhang, D. Ma, J. Li, and J. Wei, “Survey on Unmanned Aerial Vehicle Networks: A Cyber Physical System Perspective,” IEEE Commun Surv Tutorials, vol. 22, no. 2, pp. 1027–1070, 2020, doi: 10.1109/COMST.2019.2962207

    work page doi:10.1109/comst.2019.2962207 2020

  21. [21]

    Autonomous air combat decision making via graph neural networks and reinforcement learning,

    L. Huo, C. Wang, and Y. Han, “Autonomous air combat decision making via graph neural networks and reinforcement learning,” Sci Rep, vol. 15, no. 1, pp. 1–21, 2025, doi: 10.1038/s41598-025-00463-y

    work page doi:10.1038/s41598-025-00463-y 2025

  22. [22]

    Outer Space Capabilities,

    S. B. S. Review and I. Affairs, “Outer Space Capabilities,” vol. 44, no. 2, pp. 5–30, 2025

    2025

  23. [23]

    Use of Graph Neural Networks in Aiding Defensive Cyber Operations,

    S. Mitra, T. Chakraborty, S. Neupane, A. Piplai, and S. Mittal, “Use of Graph Neural Networks in Aiding Defensive Cyber Operations,” ACM Trans Priv Secur, vol. 0, no. 0, 2024

    2024

  24. [24]

    Enhancing Autonomous System Security and Resilience With Generative AI: A Comprehensive Survey,

    M. Andreoni, W. T. Lunardi, G. Lawton, and S. Thakkar, “Enhancing Autonomous System Security and Resilience With Generative AI: A Comprehensive Survey,” IEEE Access, vol. 12, no. July, pp. 109470–109493, 2024, doi: 10.1109/ACCESS.2024.3439363

    work page doi:10.1109/access.2024.3439363 2024

  25. [25]

    CONNECTED FRONTS . GAZA , ISRAEL AND IRAN IN THE NEW GEOGRAPHY OF CONFLICT Aniello Inverso Vision & Global Trends,

    A. Inverso and G. Trends, “CONNECTED FRONTS . GAZA , ISRAEL AND IRAN IN THE NEW GEOGRAPHY OF CONFLICT Aniello Inverso Vision & Global Trends,” 2025

    2025

  26. [26]

    A Comprehensive Survey on 5G-and-Beyond Networks With UAVs: Applications, Emerging Technologies, Regulatory Aspects, Research Trends and Challenges,

    M. K. Banafaa et al., “A Comprehensive Survey on 5G-and-Beyond Networks With UAVs: Applications, Emerging Technologies, Regulatory Aspects, Research Trends and Challenges,” IEEE Access, vol. 12, no. October 2023, pp. 7786–7826, 2024, doi: 10.1109/ACCESS.2023.3349208

    work page doi:10.1109/access.2023.3349208 2023

  27. [27]

    Assembling Israeli drone warfare: Loitering surveillance and operational sustainability,

    S. Borg, “Assembling Israeli drone warfare: Loitering surveillance and operational sustainability,” Secur Dialogue, vol. 52, no. 5, pp. 401–417, 2021, doi: 10.1177/0967010620956796

    work page doi:10.1177/0967010620956796 2021

  28. [28]

    Structural Shifts and Regional Security: A View from Israel,

    E. Eiran, “Structural Shifts and Regional Security: A View from Israel,” Ist Aff Internazionali, no. 2020, 2020

    2020

  29. [29]

    Stoddart, Cyberwarfare: Threats to Critical Infrastructure

    K. Stoddart, Cyberwarfare: Threats to Critical Infrastructure. 2022

    2022

  30. [30]

    The shift to defence in Israel’s hybrid military strategy,

    O. Barak, A. Sheniak, and A. Shapira, “The shift to defence in Israel’s hybrid military strategy,” J Strateg Stud, vol. 46, no. 2, pp. 345–377, 2023, doi: 10.1080/01402390.2020.1770090

    work page doi:10.1080/01402390.2020.1770090 2023

  31. [31]

    Cyber Security Threats to Iran and its Countermeasures: Defensive and Offensive Cyber Strategies,

    Syed Qandil Abbas and H. Fatima, “Cyber Security Threats to Iran and its Countermeasures: Defensive and Offensive Cyber Strategies,” J Res Soc Sci, vol. 12, no. 2, pp. 42–62, 2024, doi: 10.52015/jrss.12i2.271

    work page doi:10.52015/jrss.12i2.271 2024

  32. [32]

    the Middle East’S Game of Drones the Race To Lethal Uavs and Its Implications for the Region’S Security Landscape,

    F. Borsari, “the Middle East’S Game of Drones the Race To Lethal Uavs and Its Implications for the Region’S Security Landscape,” Ispi Anal, vol. 15, p. 2021, 2021

    2021

  33. [33]

    US-Iran Cyber war and its impact on Israel,

    M. H. Arshad, “US-Iran Cyber war and its impact on Israel,” vol. 4, no. 1, pp. 1134–1158, 2025

    2025

  34. [34]

    Intelligent automation of financ ial and accounting processes in business process outsourcing centers i n Poland,

    M. Stachoń, “Iranian Cyber Capabilities As a Tool of Domestic and Foreign Policy,” Zesz Nauk SGSP, vol. 2, no. 88, pp. 267–290, 2024, doi: 10.5604/01.3001.0054.4537

    work page doi:10.5604/01.3001.0054.4537 2024

  35. [35]

    Redefining Conflict in the AI Era: Transforming Paradigms in International Security,

    A. M. Khan, “Redefining Conflict in the AI Era: Transforming Paradigms in International Security,” J Q Res J www al-aasarcom, vol. 2, no. 1, pp. 1–14, 2025

    2025

  36. [36]

    Enhancing Resilience in Distributed ML Inference Pipelines for Edge Computing,

    U. A. Mughal, R. Atat, and M. Ismail, “Graph Neural Network-Based Intrusion Detection System for a Swarm of UAVs,” Proc - IEEE Mil Commun Conf MILCOM, pp. 578–583, 2024, doi: 10.1109/MILCOM61039.2024.10773671

    work page doi:10.1109/milcom61039.2024.10773671 2024

  37. [37]

    Graph-Powered Defense: Controller Area Network Intrusion Detection for Unmanned Aerial Vehicles

    R. Majumder Candidate et al., “Graph-Powered Defense: Controller Area Network Intrusion Detection for Unmanned Aerial Vehicles”

  38. [38]

    DEGNN: A Deep Learning-Based Method for Unmanned Aerial Vehicle Software Security Analysis,

    J. Du, Q. Wei, Y. Wang, and X. Bai, “DEGNN: A Deep Learning-Based Method for Unmanned Aerial Vehicle Software Security Analysis,” Drones, vol. 9, no. 2, 2025, doi: 10.3390/drones9020110

    work page doi:10.3390/drones9020110 2025

  39. [39]

    Unmanned Aerial Vehicle Anomaly Detection Based on Causality-Enhanced Graph Neural Networks,

    C. Feng, J. Fan, Z. Liu, G. Jin, and S. Chen, “Unmanned Aerial Vehicle Anomaly Detection Based on Causality-Enhanced Graph Neural Networks,” Drones, vol. 9, no. 6, 2025, doi: 10.3390/drones9060408

    work page doi:10.3390/drones9060408 2025

  40. [40]

    SR-GNN: Spectral Residuals with Graph Neural Networks for Anomaly Detection in ADS-B Data,

    X. Zhang and J. Li, “SR-GNN: Spectral Residuals with Graph Neural Networks for Anomaly Detection in ADS-B Data,” Commun Comput Inf Sci, vol. 1992, pp. 503–516, 2024, doi: 10.1007/978-981-99-9331-4_33

    work page doi:10.1007/978-981-99-9331-4_33 1992

  41. [41]

    An Unsupervised Graph Neural Network Approach to Deceive UAV Network Reconnaissance Attack,

    A. Njanko, D. B. Rawat, C. Kamhoua, and A. Hemida, “An Unsupervised Graph Neural Network Approach to Deceive UAV Network Reconnaissance Attack,” IEEE INFOCOM 2024 - IEEE Conf Comput Commun Work INFOCOM WKSHPS 2024, pp. 5–10, 2024, doi: 10.1109/INFOCOMWKSHPS61880.2024.10620885

    work page doi:10.1109/infocomwkshps61880.2024.10620885 2024

  42. [42]

    Adversarial Label- Flipping Attack and Defense for Anomaly Detection in Spatial Crowdsourcing UAV Services,

    J. Akram, A. Anaissi, A. Akram, R. Singh Rathore, and R. H. Jhaveri, “Adversarial Label- Flipping Attack and Defense for Anomaly Detection in Spatial Crowdsourcing UAV Services,” IEEE Trans Consum Electron, vol. 71, no. 1, pp. 2163–2174, 2025, doi: 10.1109/TCE.2024.3448541

    work page doi:10.1109/tce.2024.3448541 2025

  43. [43]

    Cyber Security Protection in Roadside Unit Based on Cross-Layer Adaptive Graph Neural Networks (Gnns) in Vanet,

    R. Kumar, S. Pandey, K. S. Asha, R. K. Yadav, A. Mishra, and S. Sharma, “Cyber Security Protection in Roadside Unit Based on Cross-Layer Adaptive Graph Neural Networks (Gnns) in Vanet,” J Cybersecurity Inf Manag, vol. 14, no. 1, p. 179, Jul. 2024, doi: 10.54216/JCIM.140112

    work page doi:10.54216/jcim.140112 2024

  44. [44]

    UGL: A comprehensive hybrid model integrating GCN and LSTM for enhanced intrusion detection in UAV controller area networks,

    Y. Du, Y. Li, P. Cheng, Z. Han, and Y. Wang, “UGL: A comprehensive hybrid model integrating GCN and LSTM for enhanced intrusion detection in UAV controller area networks,” Comput Networks, vol. 262, p. 111157, May 2025, doi: 10.1016/J.COMNET.2025.111157

    work page doi:10.1016/j.comnet.2025.111157 2025

  45. [45]

    GNN-IDS: Graph Neural Network based Intrusion Detection System,

    Z. Sun, A. M. H. Teixeira, and S. Toor, “GNN-IDS: Graph Neural Network based Intrusion Detection System,” ACM Int Conf Proceeding Ser, 2024, doi: 10.1145/3664476.3664515

    work page doi:10.1145/3664476.3664515 2024

  46. [46]

    Graphic Neural Network based GPS Spoofing Detection for Cellular-Connected UAV swarm,

    Y. Dang, A. Karakoc, and R. Jäntti, “Graphic Neural Network based GPS Spoofing Detection for Cellular-Connected UAV swarm,” IEEE Veh Technol Conf, vol. 2023-June, 2023, doi: 10.1109/VTC2023-Spring57618.2023.10200557

    work page doi:10.1109/vtc2023-spring57618.2023.10200557 2023

  47. [47]

    In: European Confer- enceonComputerVision(ECCV)(2022).https://doi.org/10.1007/978-3-031- 19842- 7_7,https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/ 136990106.pdf

    H. Friji, A. Olivereau, and M. Sarkiss, “Efficient Network Representation for GNN-Based Intrusion Detection,” Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics), vol. 13905 LNCS, pp. 532–554, 2023, doi: 10.1007/978-3-031- 33488-7_20

    work page doi:10.1007/978-3-031- 2023

  48. [48]

    GNN-Based Network Traffic Analysis for the Detection of Sequential Attacks in IoT,

    T. Altaf, X. Wang, W. Ni, G. Yu, R. P. Liu, and R. Braun, “GNN-Based Network Traffic Analysis for the Detection of Sequential Attacks in IoT,” Electron, vol. 13, no. 12, pp. 1– 18, 2024, doi: 10.3390/electronics13122274

    work page doi:10.3390/electronics13122274 2024

  49. [49]

    Thudi, G

    H. He, Y. Ji, and H. H. Huang, “Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis,” Proc - 7th IEEE Eur Symp Secur Privacy, Euro S P 2022, pp. 74–89, 2022, doi: 10.1109/EuroSP53844.2022.00013

    work page doi:10.1109/eurosp53844.2022.00013 2022

  50. [50]

    Enhancing IoT Cybersecurity with Graph Neural Networks: Advanced Anomaly Detection and Threat Mitigation,

    H. Narne, “Enhancing IoT Cybersecurity with Graph Neural Networks: Advanced Anomaly Detection and Threat Mitigation,” Int J Sci Res, vol. 12, no. 8, pp. 2571–2575, 2023, doi: 10.21275/sr23086105929

    work page doi:10.21275/sr23086105929 2023

  51. [51]

    Optimized Federated Learning for Cybersecurity : Integrating Split Learning , Graph Neural Networks , and Hashgraph Technology

    M. R. Sareddy, “Optimized Federated Learning for Cybersecurity : Integrating Split Learning , Graph Neural Networks , and Hashgraph Technology”

  52. [52]

    In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security

    F. Liu, X. Jiang, Y. Wen, X. Xing, D. Zhang, and D. Meng, “Log2vec: A heterogeneous graph embedding based approach for detecting cyber threats within enterprise,” Proc ACM Conf Comput Commun Secur, pp. 1777–1794, Nov. 2019, doi: 10.1145/3319535.3363224/SUPPL_FILE/P1777-LIU.WEBM

    work page doi:10.1145/3319535.3363224/suppl_file/p1777-liu.webm 2019

  53. [53]

    DeePMEM: Learning graph neural network models for fast and robust memory forensic analysis,

    W. Song, H. Yin, C. Liu, and D. Song, “DeePMEM: Learning graph neural network models for fast and robust memory forensic analysis,” Proc ACM Conf Comput Commun Secur, no. 2, pp. 606–618, 2018, doi: 10.1145/3243734.3243813

    work page doi:10.1145/3243734.3243813 2018

  54. [54]

    Towards the Deployment of Realistic Autonomous Cyber Network Defence: A Systematic Review,

    S. Vyas, V. Mavroudis, and P. Burnap, “Towards the Deployment of Realistic Autonomous Cyber Network Defence: A Systematic Review,” ACM Comput Surv, vol. 58, no. 1, pp. 1–36, 2025, doi: 10.1145/3729213

    work page doi:10.1145/3729213 2025

  55. [55]

    Adaptive Depth Graph Neural Network-Based Dynamic Task Allocation for UAV-UGVs Under Complex Environments,

    Z. Ma, J. Xiong, H. Gong, and X. Wang, “Adaptive Depth Graph Neural Network-Based Dynamic Task Allocation for UAV-UGVs Under Complex Environments,” IEEE Trans Intell Veh, vol. 10, no. 5, pp. 3573–3586, 2025, doi: 10.1109/TIV.2024.3457493

    work page doi:10.1109/tiv.2024.3457493 2025

  56. [56]

    Inductive representation learning on large graphs,

    W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” Adv Neural Inf Process Syst, vol. 2017-Decem, no. Nips, pp. 1025–1035, 2017

    2017

  57. [57]

    Radware reports hybrid warfare as cyberattacks, disinformation escalate in 2025 Israel- Iran conflict - Industrial Cyber

    “Radware reports hybrid warfare as cyberattacks, disinformation escalate in 2025 Israel- Iran conflict - Industrial Cyber.” Accessed: May 02, 2026. [Online]. Available: https://industrialcyber.co/threats-attacks/radware-reports-hybrid-warfare-as-cyberattacks- disinformation-escalate-in-2025-israel-iran-conflict/

    2025

  58. [58]

    How Drone Swarms Work—From Iran’s Shahed Attack to Ukraine’s Operation Spiderweb | Scientific American

    “How Drone Swarms Work—From Iran’s Shahed Attack to Ukraine’s Operation Spiderweb | Scientific American.” Accessed: May 02, 2026. [Online]. Available: https://www.scientificamerican.com/article/how-drone-swarms-work-from-irans-shahed- attack-to-ukraines-operation/

    2026

  59. [59]

    Small Drone Warfare in Iran: How Israel Infiltrated - DRONELIFE

    “Small Drone Warfare in Iran: How Israel Infiltrated - DRONELIFE.” Accessed: May 02,

  60. [60]

    Available: https://dronelife.com/2025/06/23/the-silent-invasion-how- israels-small-drones-infiltrated-iran/

    [Online]. Available: https://dronelife.com/2025/06/23/the-silent-invasion-how- israels-small-drones-infiltrated-iran/

    2025