EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Robust Cross-Sensor Image Steganalysis Framework for Robotic Telemetry in Nuclear Facilities

Mostafa Morsy Mohamed, Mohamed Ragab Salama, Ayat Taha

Computational Discovery and Intelligent Systems (CDIS) · 2026

DOI: 10.66279/neehrc96 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Discovery and Intelligent Systems (CDIS), 2026. Verfasst von Mostafa Morsy Mohamed und 2 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous robotic platforms increasingly support inspection, surveillance, and environmental monitoring at safety-critical facilities. Image telemetry from these platforms creates a potential covert channel because a payload can be embedded in otherwise legitimate frames before transmission. This study evaluates a convolutional steganalysis network, NuclearStegNet, that combines fixed Spatial Rich Model residual filters with residual attention blocks and Squeeze-and-Excitation channel weighting. The evaluation uses BOSSbase 1.01 as an optical reference source and HIT-UAV thermal imagery as a cross-sensor test source. On the supplied experimental record, NuclearStegNet reaches 89.3% accuracy for J-UNIWARD at 0.4 bits per pixel on the matched optical test condition and 82.8% under optical-to-thermal mismatch. The corresponding SRM with Ensemble Classifier baseline reaches 68.4% and 59.9%, respectively. These findings suggest that residual preprocessing and channel attention may enhance detection under the evaluated distribution shift. However, the thermal dataset is not representative of nuclear inspection imagery and cannot establish operational performance in a nuclear facility. Accordingly, the study is presented as a reproducibility focused research framework with a preliminary deployment concept, rather than as evidence of an observed attack or a validated field system.

Zitieren

APA

Mohamed, M. M., Salama, M. R., & Taha, A. (2026). A Robust Cross-Sensor Image Steganalysis Framework for Robotic Telemetry in Nuclear Facilities. Computational Discovery and Intelligent Systems (CDIS). https://doi.org/10.66279/neehrc96

Vancouver

Mohamed MM, Salama MR, Taha A. A Robust Cross-Sensor Image Steganalysis Framework for Robotic Telemetry in Nuclear Facilities. Computational Discovery and Intelligent Systems (CDIS). 2026. doi:10.66279/neehrc96

BibTeX
@article{Mohamed2026,
  author = {Mohamed, Mostafa Morsy and Salama, Mohamed Ragab and Taha, Ayat},
  title = {A Robust Cross-Sensor Image Steganalysis Framework for Robotic Telemetry in Nuclear Facilities},
  journal = {Computational Discovery and Intelligent Systems (CDIS)},
  year = {2026},
  doi = {10.66279/neehrc96}
}
Kostenlos starten →