2021 IEEE International Conference on Cyber Security and Resilience

Full Program

Summary:

The widespread use of powerful mobile devices has deeply affected the network traffic. Traffic encryption has become extremely common and the proliferation of mobile apps have created a challenging scenario for traffic classification and its uses especially network-security related ones. The recent rise of Deep Learning (DL) has responded to this challenge. However the lack of interpretability of these black-box approaches limits or prevents their adoption in contexts where the reliability of results or interpretability of polices is necessary.
To cope with these limitations eXplainable Artificial Intelligence (XAI) techniques have seen recent intensive research. Along these lines, our work applies XAI-based techniques to interpret the behavior of a state-of-art multimodal DL traffic classifier. As opposed to common results seen in XAI we aim at a global interpretation rather than sample-based ones. The results quantify the importance of each modality and of specific subsets of inputs in determining the classification outcome.

Author(s):

Alfredo Nascita    
University of Napoli Federico II
Italy

Antonio Montieri    
University of Napoli Federico II
Italy

Giuseppe Aceto    
University of Napoli Federico II
Italy

Domenico Ciuonzo    
University of Napoli Federico II
Italy

Valerio Persico    
University of Napoli Federico II
Italy

Antonio Pescape    
University of Napoli Federico II
Italy

 


Copyright © 2021 SUMMIT-TEC GROUP LTD