pith. machine review for the scientific record. sign in

arxiv: 2604.06411 · v1 · submitted 2026-04-07 · 💻 cs.CR · cs.AI· cs.GL· cs.LG

Recognition: no theorem link

Towards Resilient Intrusion Detection in CubeSats: Challenges, TinyML Solutions, and Future Directions

Yasamin Fayyaz , Li Yang , Khalil El-Khatib
Authors on Pith no claims yet

Pith reviewed 2026-05-10 18:34 UTC · model grok-4.3

classification 💻 cs.CR cs.AIcs.GLcs.LG
keywords CubeSatsTinyMLintrusion detectioncybersecurityanomaly detectionspace systemsresource constraintsmachine learning
0
0 comments X

The pith

TinyML offers resource-efficient real-time intrusion detection for CubeSats facing cybersecurity risks from commercial components.

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

CubeSats rely on commercial off-the-shelf parts and open-source software, which introduce cybersecurity vulnerabilities that standard intrusion detection systems cannot manage given tight limits on power, memory, and processing power. The paper reviews existing cybersecurity practices for these satellites, points out their limitations, and surveys anomaly detection methods from non-cyber fields for techniques that could adapt to CubeSat constraints. It positions the addition of TinyML as a promising route to onboard, lightweight models that detect intrusions in real time without exceeding hardware budgets. A reader would care because CubeSats now support an expanding range of space missions, and unresolved security gaps risk mission loss or compromised data. The review closes by naming open problems such as realistic scenario testing and combining security with health monitoring.

Core claim

The paper reviews cybersecurity practices for CubeSats and concludes that traditional intrusion detection systems prove impractical due to resource constraints and unique space environments. It identifies gaps and explores non-cyber anomaly detection techniques for adaptable algorithms and strategies. The central proposal is that incorporating TinyML into CubeSat systems supplies a promising solution by enabling resource-efficient, real-time intrusion detection capabilities, with proposed future directions including integration with health monitoring and cross-domain collaboration.

What carries the argument

TinyML models optimized for tiny devices, deployed for on-board intrusion detection to handle the constraints of CubeSat hardware and operations.

If this is right

  • Resource-efficient intrusion detection mechanisms become feasible for CubeSats without exceeding hardware limits.
  • IDS solutions gain the possibility of evaluation under realistic mission scenarios.
  • Autonomous response systems for detected intrusions can be developed.
  • Tailored cybersecurity frameworks for CubeSats can be created.
  • Integration of intrusion detection with existing health monitoring systems becomes practical.

Where Pith is reading between the lines

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

  • Successful deployment could allow CubeSats to handle security decisions with less reliance on ground stations.
  • The same lightweight model approach might transfer to other small embedded platforms facing similar limits, such as certain IoT devices.
  • Empirical runs on flight hardware would be needed to confirm performance under radiation or temperature extremes.
  • Emphasized collaboration between fields could produce shared security standards for future commercial satellites.

Load-bearing premise

TinyML models can be practically adapted and deployed on CubeSat hardware to deliver effective intrusion detection under realistic mission constraints.

What would settle it

A test on CubeSat-equivalent hardware that shows a TinyML intrusion detector either failing to catch attacks or exceeding available power and memory during a realistic mission simulation would falsify the proposed solution.

Figures

Figures reproduced from arXiv: 2604.06411 by Khalil El-Khatib, Li Yang, Yasamin Fayyaz.

Figure 1
Figure 1. Figure 1: Annual CubeSat launches from 1998 to 2025. Counts [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Taxonomy of cybersecurity threats and attacks targeting [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Example of pruning techniques applied to a neural [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Example of the quantization process applied to neural [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Example of weight clustering in a neural network. The [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustrative CASH trade-off for TinyML deployment, [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Example TinyML-enabled Host-based IDS Workflow [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
read the original abstract

CubeSats have revolutionized access to space by providing affordable and accessible platforms for research and education. However, their reliance on Commercial Off-The-Shelf (COTS) components and open-source software has introduced significant cybersecurity vulnerabilities. Ensuring the cybersecurity of CubeSats is vital as they play increasingly important roles in space missions. Traditional security measures, such as intrusion detection systems (IDS), are impractical for CubeSats due to resource constraints and unique operational environments. This paper provides an in-depth review of current cybersecurity practices for CubeSats, highlighting limitations and identifying gaps in existing methods. Additionally, it explores non-cyber anomaly detection techniques that offer insights into adaptable algorithms and deployment strategies suitable for CubeSat constraints. Open research problems are identified, including the need for resource-efficient intrusion detection mechanisms, evaluation of IDS solutions under realistic mission scenarios, development of autonomous response systems, and creation of cybersecurity frameworks. The addition of TinyML into CubeSat systems is explored as a promising solution to address these challenges, offering resource-efficient, real-time intrusion detection capabilities. Future research directions are proposed, such as integrating cybersecurity with health monitoring systems, and fostering collaboration between cybersecurity researchers and space domain experts.

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 manuscript is a survey reviewing cybersecurity vulnerabilities in CubeSats arising from COTS components and open-source software, limitations of traditional IDS under resource constraints, insights from non-cyber anomaly detection literature, open problems (resource-efficient IDS, realistic evaluation, autonomous response, frameworks), and the positioning of TinyML as a promising direction for real-time, efficient intrusion detection, with suggestions to integrate cybersecurity with health monitoring and foster cross-domain collaboration.

Significance. If the synthesis of literature and gap identification holds, the paper could usefully direct future work on space-system security by framing TinyML as a candidate for constrained environments; however, the absence of any new data, models, simulations, or deployment results limits its immediate impact to that of a problem-statement review rather than a contribution with testable advances.

major comments (2)
  1. [Abstract and TinyML section] Abstract and the TinyML exploration section: the assertion that TinyML 'offers resource-efficient, real-time intrusion detection capabilities' for CubeSats is presented as a solution without any CubeSat-specific adaptation analysis, hardware benchmarks, model-size estimates, or references to prior TinyML deployments on comparable embedded platforms; this claim is load-bearing for the paper's central forward-looking argument yet rests only on general TinyML properties.
  2. [Open research problems and future directions] Open research problems and future directions section: the call for 'evaluation of IDS solutions under realistic mission scenarios' is identified as a gap, but the manuscript itself performs no such evaluation or even a high-level feasibility mapping of TinyML models to typical CubeSat power, compute, and communication profiles, leaving the proposed direction unsubstantiated.
minor comments (2)
  1. [Anomaly detection survey] The survey of anomaly-detection techniques would benefit from a concise table comparing resource requirements, detection latency, and adaptability to the CubeSat constraints listed earlier in the paper.
  2. [TinyML discussion] Several citations to general TinyML literature appear without explicit discussion of their relevance to radiation-hardened or low-power space hardware; adding one or two sentences clarifying transferability would improve clarity.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey manuscript. The comments help clarify the scope and framing of our discussion on CubeSat cybersecurity challenges and the potential role of TinyML. We address each major comment below and outline revisions to improve precision without altering the paper's review nature.

read point-by-point responses

  1. Referee: [Abstract and TinyML section] Abstract and the TinyML exploration section: the assertion that TinyML 'offers resource-efficient, real-time intrusion detection capabilities' for CubeSats is presented as a solution without any CubeSat-specific adaptation analysis, hardware benchmarks, model-size estimates, or references to prior TinyML deployments on comparable embedded platforms; this claim is load-bearing for the paper's central forward-looking argument yet rests only on general TinyML properties.

    Authors: We agree that the manuscript, being a survey, does not introduce original CubeSat-specific adaptation analyses, benchmarks, or model estimates. The positioning of TinyML draws from its documented properties in resource-constrained embedded systems (as synthesized from the broader literature) alongside the CubeSat constraints reviewed in earlier sections. To address the concern, we will revise the abstract and TinyML section to frame the approach more explicitly as a promising research direction that requires further CubeSat-tailored investigation, while adding references to existing TinyML deployments on comparable embedded platforms to better support the discussion. revision: yes

  2. Referee: [Open research problems and future directions] Open research problems and future directions section: the call for 'evaluation of IDS solutions under realistic mission scenarios' is identified as a gap, but the manuscript itself performs no such evaluation or even a high-level feasibility mapping of TinyML models to typical CubeSat power, compute, and communication profiles, leaving the proposed direction unsubstantiated.

    Authors: The open problems section is intended to delineate gaps for future work, consistent with the objectives of a review paper; we do not perform or claim new evaluations. We acknowledge that a high-level feasibility mapping would strengthen the substantiation of the proposed directions. In revision, we will incorporate such a preliminary mapping based on publicly available CubeSat hardware profiles and TinyML performance characteristics from the literature, while clearly stating that detailed, mission-specific evaluations remain an open challenge. revision: partial

Circularity Check

0 steps flagged

No significant circularity; survey paper with no internal derivations

full rationale

The manuscript is a literature review summarizing CubeSat cybersecurity challenges, surveying external anomaly-detection and IDS techniques, and identifying open problems while suggesting TinyML integration as a future direction. No equations, fitted parameters, predictions, or derivations appear in the text; all assertions about resource-efficient capabilities draw from cited external literature rather than reducing to the paper's own inputs or self-citations. This is a standard non-derivational survey structure with no load-bearing steps that could exhibit circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a review paper, the content rests on synthesis of existing cybersecurity and TinyML literature rather than new postulates. No free parameters, axioms, or invented entities are introduced by the authors themselves.

pith-pipeline@v0.9.0 · 5521 in / 1026 out tokens · 56658 ms · 2026-05-10T18:34:26.034634+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

48 extracted references · 2 canonical work pages

  1. [1]

    CubeSat 101: Basic concepts and processes for first-time CubeSat developers

    NASA, “CubeSat 101: Basic concepts and processes for first-time CubeSat developers.” https://www.nasa.gov/wp-content/uploads/2017/ 03/nasa csli cubesat 101 508.pdf, 2017. Accessed: 2024-12-01

    2017

  2. [2]

    Nanosats database

    E. Kulu, “Nanosats database.” http://www.nanosats.eu, 2025. Accessed: 2025-12-20

    2025

  3. [3]

    Physics-informed satellite cybersecurity,

    M. Calabrese, G. Falco, and D. Serpanos, “Physics-informed satellite cybersecurity,”Computer, vol. 57, no. 5, pp. 106–109, 2024

    2024

  4. [4]

    AWS ground station

    Amazon Web Services, “AWS ground station.” https://aws.amazon.com/ ground-station/, 2024. Accessed: 2024-12-01

    2024

  5. [5]

    CubeSat communications: Recent advances and future challenges,

    N. Saeed, A. M. Elzanaty, H. Almorad, H. Dahrouj, T. Y . Al-Naffouri, and M.-S. Alouini, “CubeSat communications: Recent advances and future challenges,”IEEE Communications Surveys & Tutorials, vol. 22, pp. 1839–1862, 2019

    2019

  6. [6]

    Intrusion detection system for CubeSats: A survey,

    O. Driouch, S. Bah, and Z. Guennoun, “Intrusion detection system for CubeSats: A survey,” in2023 International Wireless Communications and Mobile Computing (IWCMC), pp. 596–601, 2023

    2023

  7. [7]

    CubeSat security attack tree analysis,

    G. Falco, A. Viswanathan, and A. Santangelo, “CubeSat security attack tree analysis,” in2021 IEEE 8th International Conference on Space Mission Challenges for Information Technology (SMC-IT), pp. 68–76, 2021

    2021

  8. [8]

    Space odyssey: An experimental software security analysis of satellites,

    J. Willbold, M. Schloegel, M. V ¨ogele, M. Gerhardt, T. Holz, and A. Abbasi, “Space odyssey: An experimental software security analysis of satellites,” in2023 IEEE Symposium on Security and Privacy (SP), pp. 1–19, IEEE, 2023

    2023

  9. [9]

    Overview on intrusion detection systems for computers networking security,

    L. Diana, P. Dini, and D. Paolini, “Overview on intrusion detection systems for computers networking security,”Computers, vol. 14, no. 3, p. 87, 2025

    2025

  10. [10]

    Anomaly detection based on artificial intelligence of things: A systematic literature mapping,

    S. Trilles, S. S. Hammad, and D. Iskandaryan, “Anomaly detection based on artificial intelligence of things: A systematic literature mapping,” Internet of Things, vol. 25, p. 101063, 2024

    2024

  11. [11]

    Calabrese, G

    M. Calabrese, G. Kavallieratos, and G. Falco,A Hosted Payload Cyber Attack Against Satellites. 01 2024

    2024

  12. [12]

    HACK: A holistic modeling approach for CubeSat cyberattacks,

    S. Borgia, F. Topputo, and S. Zanero, “HACK: A holistic modeling approach for CubeSat cyberattacks,” inAerospace Science and En- gineering: III Aerospace PhD-Days, vol. 33 ofMaterials Research Proceedings, pp. 281–287, Materials Research Forum LLC, 2023

    2023

  13. [13]

    OPS-SAT: Operational concept for ESA’s first mission dedicated to operational technology,

    D. J. Evans, “OPS-SAT: Operational concept for ESA’s first mission dedicated to operational technology,” in14th International Conference on Space Operations, p. 2354, 2016

    2016

  14. [14]

    The LinkStar cy- bersecurity “sandbox

    A. D. Santangelo, G. Falco, and A. Viswanathan, “The LinkStar cy- bersecurity “sandbox”: A platform to test small satellite vulnerabilities within the community – updates and lessons learned,” inAIAA SciTech 2022 Forum, American Institute of Aeronautics and Astronautics, Jan

    2022

  15. [15]

    AIAA Paper 2022-0239

    2022

  16. [16]

    Developing scenarios sup- porting space-based IDS,

    J. P. Thebarge, W. Henry, and G. Falco, “Developing scenarios sup- porting space-based IDS,” inASCEND 2022, American Institute of Aeronautics and Astronautics, Oct. 2022. AIAA Paper 2022-4219

    2022

  17. [17]

    Distributed intrusion detection system for CubeSats, based on deep learning packets classification model,

    O. Driouch, S. Bah, and Z. Guennoun, “Distributed intrusion detection system for CubeSats, based on deep learning packets classification model,” in2024 Security for Space Systems (3S), pp. 1–8, IEEE, 2024

    2024

  18. [18]

    UA VCAN intrusion dataset

    D. Kim, Y . Song, S. Kwon, H. Kim, J. D. Yoo, and H. K. Kim, “UA VCAN intrusion dataset.” https://dx.doi.org/10.21227/fcyc-bb14, 2025

    work page doi:10.21227/fcyc-bb14 2025

  19. [19]

    Case-based reasoning for system anomaly detection and management,

    S. Ramachandran and C. Belardi, “Case-based reasoning for system anomaly detection and management,” in2021 IEEE Aerospace Con- ference (50100), pp. 1–9, IEEE, 2021. 14

    2021

  20. [20]

    Performance evaluation of machine learning methods for anomaly detection in CubeSat solar panels,

    A. J. J. Cespedes, B. H. B. Pangestu, A. Hanazawa, and M. Cho, “Performance evaluation of machine learning methods for anomaly detection in CubeSat solar panels,”Applied Sciences, vol. 12, no. 17, p. 8634, 2022

    2022

  21. [21]

    Anomaly detection using deep learning respecting the resources on board a CubeSat,

    R. Horne, S. Mauw, A. Mizera, A. Stemper, and J. Thoemel, “Anomaly detection using deep learning respecting the resources on board a CubeSat,”Journal of Aerospace Information Systems, vol. 20, no. 12, pp. 859–872, 2023

    2023

  22. [22]

    Machine learning detects anomalies in OPS-SAT telemetry,

    B. Ruszczak, K. Kotowski, J. Andrzejewski, A. Musiał, D. Evans, V . Zelenevskiy, S. Bammens, R. Laurinovics, and J. Nalepa, “Machine learning detects anomalies in OPS-SAT telemetry,” inInternational Conference on Computational Science, pp. 295–306, Springer, 2023

    2023

  23. [23]

    Toward on-board detection of anomalous events from OPS-SAT telemetry using deep learning,

    J. Nalepa, J. Andrzejewski, B. Ruszczak, K. Kotowski, A. Musiał, D. Evans, V . Zelenevskiy, S. Bammens, and R. Laurinovics, “Toward on-board detection of anomalous events from OPS-SAT telemetry using deep learning,” inPresented at the 8th international workshop on on- board payload data compression, p. 7, Zenodo, Athens, 2022

    2022

  24. [24]

    OPS-SAT spacecraft autonomy with TensorFlow lite, unsupervised learning, and online machine learning,

    G. Labr `eche, D. Evans, D. Marszk, T. Mladenov, V . Shiradhonkar, T. Soto, and V . Zelenevskiy, “OPS-SAT spacecraft autonomy with TensorFlow lite, unsupervised learning, and online machine learning,” in2022 IEEE Aerospace Conference (AERO), pp. 1–17, IEEE, 2022

    2022

  25. [25]

    Energy budgeting for CubeSats with an integrated FPGA,

    S. S. Arnold, R. Nuzzaci, and A. Gordon-Ross, “Energy budgeting for CubeSats with an integrated FPGA,” in2012 IEEE Aerospace Conference, pp. 1–14, 2012

    2012

  26. [26]

    Onboard processing with hybrid and reconfigurable computing on small satellites,

    A. D. George and C. M. Wilson, “Onboard processing with hybrid and reconfigurable computing on small satellites,”Proceedings of the IEEE, vol. 106, no. 3, pp. 458–470, 2018

    2018

  27. [27]

    CubeSat communication di- rection and capabilities at morehead state university and NASA goddard space flight center, wallops flight facility,

    S. Schaire, S. Altunc, and B. Malphrus, “CubeSat communication di- rection and capabilities at morehead state university and NASA goddard space flight center, wallops flight facility,” inProceedings of the CubeSat Developers’ Workshop, (Logan, UT, USA), 08 2013. Small Satellite Conference, DigitalCommons@USU

    2013

  28. [28]

    Kaushal, V

    H. Kaushal, V . K. Jain, and S. Kar,Acquisition, Tracking, and Pointing, pp. 119–137. New Delhi: Springer India, 2017

    2017

  29. [29]

    Space attack research & tactic analysis

    The Aerospace Corporation, “Space attack research & tactic analysis.” https://sparta.aerospace.org. Accessed: 2024-12-01

    2024

  30. [30]

    A comprehensive survey on TinyML,

    Y . Abadade, A. Temouden, H. Bamoumen, N. Benamar, Y . Chtouki, and A. S. Hafid, “A comprehensive survey on TinyML,”IEEE Access, vol. 11, pp. 96892–96922, 2023

    2023

  31. [31]

    Structured pruning of deep convolutional neural networks,

    S. Anwar, K. Hwang, and W. Sung, “Structured pruning of deep convolutional neural networks,”Journal of Emerging Technologies in Computing Systems, vol. 13, no. 3, 2017

    2017

  32. [32]

    Advances in the neural network quantization: A comprehensive review,

    L. Wei, Z. Ma, C. Yang, and Q. Yao, “Advances in the neural network quantization: A comprehensive review,”Applied Sciences, vol. 14, no. 17, p. 7445, 2024

    2024

  33. [33]

    Chapter 9 - scalar quantization,

    K. Sayood, “Chapter 9 - scalar quantization,” inIntroduction to Data Compression (Fifth Edition)(K. Sayood, ed.), The Morgan Kaufmann Series in Multimedia Information and Systems, pp. 257–298, Morgan Kaufmann, fifth edition ed., 2018

    2018

  34. [34]

    Tiny machine learning for resource- constrained microcontrollers,

    R. Immonen and T. H ¨am¨al¨ainen, “Tiny machine learning for resource- constrained microcontrollers,”Journal of Sensors, vol. 2022, no. 1, p. 7437023, 2022

    2022

  35. [35]

    Lin,Efficient Algorithms and Systems for Tiny Deep Learning

    J. Lin,Efficient Algorithms and Systems for Tiny Deep Learning. PhD thesis, Massachusetts Institute of Technology, 2021

    2021

  36. [36]

    Auto- WEKA: Combined selection and hyperparameter optimization of clas- sification algorithms,

    C. Thornton, F. Hutter, H. H. Hoos, and K. Leyton-Brown, “Auto- WEKA: Combined selection and hyperparameter optimization of clas- sification algorithms,” inProceedings of the 19th ACM SIGKDD inter- national conference on Knowledge discovery and data mining, pp. 847– 855, 2013

    2013

  37. [37]

    Tiny machine learning: Progress and futures [feature],

    J. Lin, L. Zhu, W.-M. Chen, W.-C. Wang, and S. Han, “Tiny machine learning: Progress and futures [feature],”IEEE Circuits and Systems Magazine, vol. 23, no. 3, pp. 8–34, 2023

    2023

  38. [38]

    TinyOL: TinyML with online- learning on microcontrollers,

    H. Ren, D. Anicic, and T. A. Runkler, “TinyOL: TinyML with online- learning on microcontrollers,” in2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2021

    2021

  39. [39]

    TinyFedTL: Federated transfer learning on ubiquitous tiny IoT devices,

    K. Kopparapu, E. Lin, J. G. Breslin, and B. Sudharsan, “TinyFedTL: Federated transfer learning on ubiquitous tiny IoT devices,” in2022 IEEE International Conference on Pervasive Computing and Commu- nications Workshops and other Affiliated Events (PerCom Workshops), pp. 79–81, IEEE, 2022

    2022

  40. [40]

    IoT data analytics in dynamic environments: From an automated machine learning perspective,

    L. Yang and A. Shami, “IoT data analytics in dynamic environments: From an automated machine learning perspective,”Engineering Appli- cations of Artificial Intelligence, vol. 116, p. 105366, 2022

    2022

  41. [41]

    Machine learning for microcontroller-class hardware: A review,

    S. S. Saha, S. S. Sandha, and M. Srivastava, “Machine learning for microcontroller-class hardware: A review,”IEEE Sensors Journal, vol. 22, no. 22, pp. 21362–21390, 2022

    2022

  42. [42]

    On TinyML and cybersecurity: Electric vehicle charging infrastructure use case,

    F. Dehrouyeh, L. Yang, F. B. Ajaei, and A. Shami, “On TinyML and cybersecurity: Electric vehicle charging infrastructure use case,”arXiv preprint arXiv:2404.16894, 2024

    work page arXiv 2024

  43. [43]

    Tiny machine learning for concept drift,

    S. Disabato and M. Roveri, “Tiny machine learning for concept drift,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 6, pp. 8470–8481, 2024

    2024

  44. [44]

    Improving model robust- ness by adaptively correcting perturbation levels with active queries,

    K.-P. Ning, L. Tao, S. Chen, and S.-J. Huang, “Improving model robust- ness by adaptively correcting perturbation levels with active queries,” in Proceedings of the AAAI conference on artificial intelligence, vol. 35, pp. 9161–9169, 2021

    2021

  45. [45]

    The vacuum of space cyber security,

    G. Falco, “The vacuum of space cyber security,” in2018 AIAA SPACE and Astronautics Forum and Exposition, American Institute of Aeronau- tics and Astronautics, Sept. 2018. AIAA Paper 2018-5275

    2018

  46. [46]

    The OPS-SAT benchmark for detecting anomalies in satellite telemetry,

    B. Ruszczak, K. Kotowski, D. Evans, and J. Nalepa, “The OPS-SAT benchmark for detecting anomalies in satellite telemetry,”Scientific Data, vol. 12, no. 1, p. 710, 2025

    2025

  47. [47]

    Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization,

    I. Sharafaldin, A. Lashkari, and A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization,” in Intl Conf. on Information Systems Security and Privacy (ICISSP), vol. 1, pp. 108–116, January 2018

    2018

  48. [48]

    Space Packet Pro- tocol. Recommended Standard CCSDS 133.0-B-2,

    Consultative Committee for Space Data Systems, “Space Packet Pro- tocol. Recommended Standard CCSDS 133.0-B-2,” tech. rep., CCSDS Secretariat, Washington, D.C., June 2020

    2020