Evading behavioral classifiers: a comprehensive analysis on evading ransomware detection techniques

F De Gaspari, D Hitaj, G Pagnotta, L De Carli… - Neural Computing and …, 2022 - Springer
Recent progress in machine learning has led to promising results in behavioral malware
detection. Behavioral modeling identifies malicious processes via features derived by their …

Adversarial Challenges in Network Intrusion Detection Systems: Research Insights and Future Prospects

S Ennaji, F De Gaspari, D Hitaj, A Kbidi… - arxiv preprint arxiv …, 2024 - arxiv.org
Machine learning has brought significant advances in cybersecurity, particularly in the
development of Intrusion Detection Systems (IDS). These improvements are mainly …

Do you trust your model? emerging malware threats in the deep learning ecosystem

D Hitaj, G Pagnotta, F De Gaspari, S Ruko… - arxiv preprint arxiv …, 2024 - arxiv.org
Training high-quality deep learning models is a challenging task due to computational and
technical requirements. A growing number of individuals, institutions, and companies …

Comparison of entropy calculation methods for ransomware encrypted file identification

SR Davies, R Macfarlane, WJ Buchanan - Entropy, 2022 - mdpi.com
Ransomware is a malicious class of software that utilises encryption to implement an attack
on system availability. The target's data remains encrypted and is held captive by the …

MaleficNet: Hiding malware into deep neural networks using spread-spectrum channel coding

D Hitaj, G Pagnotta, B Hitaj, LV Mancini… - … on Research in …, 2022 - Springer
The training and development of good deep learning models is often a challenging task,
thus leading individuals (developers, researchers, and practitioners alike) to use third-party …

Minerva: A file-based ransomware detector

D Hitaj, G Pagnotta, F De Gaspari, L De Carli… - arxiv preprint arxiv …, 2023 - arxiv.org
Ransomware is a rapidly evolving type of malware designed to encrypt user files on a
device, making them inaccessible in order to exact a ransom. Ransomware attacks resulted …

Passflow: guessing passwords with generative flows

G Pagnotta, D Hitaj, F De Gaspari… - 2022 52nd Annual …, 2022 - ieeexplore.ieee.org
Recent advances in generative machine learning models rekindled research interest in the
area of password guessing. Data-driven password guessing approaches based on GANs …

Combining raw data and engineered features for optimizing encrypted and compressed internet of things traffic classification

MM Saleh, M AlSlaiman, MI Salman, B Wang - Computers & Security, 2023 - Elsevier
Abstract The Internet of Things (IoT) is used in many fields that generate sensitive data, such
as healthcare and surveillance. The increased reliance on IoT raised serious information …

Fedcomm: Federated learning as a medium for covert communication

D Hitaj, G Pagnotta, B Hitaj… - … on Dependable and …, 2023 - ieeexplore.ieee.org
Proposed as a solution to mitigate the privacy implications related to the adoption of deep
learning, Federated Learning (FL) enables large numbers of participants to successfully …

Have You Poisoned My Data? Defending Neural Networks Against Data Poisoning

F De Gaspari, D Hitaj, LV Mancini - European Symposium on Research in …, 2024 - Springer
The unprecedented availability of training data fueled the rapid development of powerful
neural networks in recent years. However, the need for such large amounts of data leads to …