SINNER
A Reward-Sensitive Algorithm for Imbalanced Malware Classification Using Neural Networks with Experience Replay
24/07/2024
The research report “SINNER: A Reward-Sensitive Algorithm for Imbalanced Malware Classification Using Neural Networks with Experience Replay.” was published, in Open Access mode, on volume 15/2024 of the journal “Information”, within the special issue “Machine Learning Approaches for Imbalanced Domains: Emerging Trends and Applications”.
An innovative algorithm
The research, carried out by colleagues Antonio Coscia, Antonio Maci, Andrea Iannacone and Alessandro Stamerra of the Cyber Lab in Grottaglie, is born within the scope of the activities provided for by the Program Contract “Cybersecurity and SOC Product Suite”, and proposes an innovative algorithm based on the use of Deep Reinforcement Learning techniques to significantly improve malware recognition and classification capabilities acting on the training phase in the case, The training data set is a very unbalanced one. The proposed algorithm has already been integrated into the prototypes of the security components of the BV TECH Cybersuite.
The research activity that led to the definition and testing of the algorithm was carried out entirely by BV TECH, a testament to the capabilities and expertise of the BV TECH Cyber Lab in analyzing and employing the most advanced Artificial Intelligence-based mechanisms in the context of cybersecurity.
GROTTAGLIE:
Corso Europa, 3
74023 Grottaglie (TA)
Tel.: +39.02.8596171
Fax: +39.02.89093321
RUTIGLIANO:
S.P. 84 Adelfia-Rutigliano, C.da Caggiano
70018 Rutigliano (BA)
Tel.: +39.02.8596171
Fax: +39.02.89093321
Project funded by the European Regional Development Fund Puglia POR Puglia 2014 - 2020 - Axis I - Specific Objective 1a - Action 1.1 (R&D), and with the support of the University of Bari and the Massachusetts Institute of Technology (MIT).