Alessandro Stamerra

Dr. Alessandro Stamerra

Cybersecurity Lab, R&D, BV TECH S.p.A., Milan, Lombardy, Italy
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 July 2024 in Information
Verified
Journal Article
Open access
PDF file
ACAntonio Coscia
Antonio Coscia
AIAndrea Iannacone
Andrea Iannacone
Antonio MaciAntonio Maci
Antonio Maci
ASAlessandro Stamerra
Alessandro Stamerra
Reports produced by popular malware analysis services showed a disparity in samples available for different malware families. The unequal distribution between such classes can be attributed to several factors, such as technological advances and the application domain that seeks to infect a computer virus. Recent studies have demonstrated the effectiveness of deep learning (DL) algorithms when learning multi-class classification tasks using imbalanced datasets. This can be achieved by updating the learning function such that correct and incorrect predictions performed on the minority class are more rewarded or penalized, respectively. This procedure can be logically implemented by leveraging the deep reinforcement learning (DRL) paradigm through a proper formulation of the Markov decision process (MDP). This paper proposes SINNER, i.e., a DRL-based multi-class classifier that approaches the data imbalance problem at the algorithmic level by exploiting a redesigned reward function, which modifies the traditional MDP model used to learn this task. Based on the experimental results, the proposed formula appears to be successful. In addition, SINNER has been compared to several DL-based models that can handle class skew without relying on data-level techniques. Using three out of four datasets sourced from the existing literature, the proposed model achieved state-of-the-art classification performance.

5 February 2025
Verified
Conference Paper
Closed access
SGStefano Galantucci
Stefano Galantucci
AIAndrea Iannacone
Andrea Iannacone
GPGiuseppe Pirlo
Giuseppe Pirlo
LSLucia Sarcinella
Lucia Sarcinella
ASAlessandro Stamerra
Alessandro Stamerra
One of the main challenges of cybersecurity is the detection and classification of malware to prevent damage to systems by both companies and private users. Identifying the specific type of malware is critical to performing targeted actions. This study proposes a classification approach that generates synthetic images of malware using Conditional Generative Adversarial Networks (cGAN) and Wasserstein Generative Adversarial Networks (WGAN). Using the Malimg dataset, consisting of 25 malware classes, the ResNet50 model shows an overall accuracy of $\mathbf{9 1. 4 \%}$ and an $\mathbf{F 1}$-score of $\mathbf{9 0. 8 \%}$ for synthetic images generated with WGAN. Resizing and resampling were employed as preprocessing strategies to obtain images of size $48 \times 48$; resampling has been shown to be more effective. Thus, the proposed methodology allows malware to be classified quickly and efficiently, and, on the other hand, unbalanced datasets can be enriched to aid classification performance.


13 May 2023
Verified
Conference Paper
Closed access
CCC. Catalano
C. Catalano
APA. Pagano
A. Pagano
APA. Piccinno
A. Piccinno
ASAlessandro Stamerra
Alessandro Stamerra