Split Computing has emerged as a promising paradigm for deploying Deep Neural Networks in Edge and Internet of Things systems, enabling inference tasks to be distributed between resource constrained edge devices and cloud servers. This approach is particularly attractive for autonomous systems applications, where security and reliability may be critical. However, intermediate feature maps transmitted between devices are vulnerable to corruption, which may result from intentional adversarial attacks or unintentional hardware faults. Distinguishing whether corruption originates from an external adversary or an inherent system fault is crucial for implementing appropriate countermeasure, reinforcing security mechanisms against attacks or improving system reliability to mitigate the effects of hardware related faults. To the best of our knowledge, this work is the first to propose a machine learning-based classification mechanism capable of differentiating adversarial attacks from hardware defects in Split Computing systems. The proposed approach analyzes the intermediate feature maps transmitted from the edge device to the server, identifying the source of corruption to guide appropriate responses. Experimental results demonstrate that one of the proposed classifiers can distinguish between intentional and unintentional feature map corruptions with an accuracy of 93.91%.

AI-based Classification of Intentional vs. Unintentional Corruptions in the Split Computing context / Esposito, Giuseppe; Magliano, Enrico; Scarano, Nicola; Ahmed-Eltaras, Tamer; Guerrero-Balaguera, Juan-David; Mannella, Luca; Rodriguez-Condia, Josie-Esteban; Ruospo, Annachiara; Di Carlo, Stefano; Levorato, Marco; Savino, Alessandro; Sonza Reorda, Matteo. - (2025), pp. 1-7. (Intervento presentato al convegno 2025 IEEE 31st International Symposium on On-Line Testing and Robust System Design (IOLTS) tenutosi a Ischia, Naples, Italy nel 7-9 July 2025) [10.1109/IOLTS65288.2025.11116959].

AI-based Classification of Intentional vs. Unintentional Corruptions in the Split Computing context

Esposito, Giuseppe;Magliano, Enrico;Scarano, Nicola;Ahmed-Eltaras,Tamer;Guerrero-Balaguera, Juan-David;Mannella, Luca;Rodriguez-Condia, Josie-Esteban;Ruospo, Annachiara;Di Carlo, Stefano;Levorato, Marco;Savino, Alessandro;Sonza Reorda, Matteo
2025

Abstract

Split Computing has emerged as a promising paradigm for deploying Deep Neural Networks in Edge and Internet of Things systems, enabling inference tasks to be distributed between resource constrained edge devices and cloud servers. This approach is particularly attractive for autonomous systems applications, where security and reliability may be critical. However, intermediate feature maps transmitted between devices are vulnerable to corruption, which may result from intentional adversarial attacks or unintentional hardware faults. Distinguishing whether corruption originates from an external adversary or an inherent system fault is crucial for implementing appropriate countermeasure, reinforcing security mechanisms against attacks or improving system reliability to mitigate the effects of hardware related faults. To the best of our knowledge, this work is the first to propose a machine learning-based classification mechanism capable of differentiating adversarial attacks from hardware defects in Split Computing systems. The proposed approach analyzes the intermediate feature maps transmitted from the edge device to the server, identifying the source of corruption to guide appropriate responses. Experimental results demonstrate that one of the proposed classifiers can distinguish between intentional and unintentional feature map corruptions with an accuracy of 93.91%.
2025
979-8-3315-3334-2
File in questo prodotto:
File Dimensione Formato  
_IOLTS_2025__Split_Reliabiliy_and_Security-6.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 1.03 MB
Formato Adobe PDF
1.03 MB Adobe PDF Visualizza/Apri
AI-Based_Classification_of_Adversarial_Attacks_vs._Hardware_Fault_Corruptions_in_the_Split_Computing_Context.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.1 MB
Formato Adobe PDF
1.1 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/3003794