Details

Autor(en) / Beteiligte

• AbdulsalamYa'u, Gital
• Job, Goteng Kuwunidi
• Waziri, Saleh Mustapha
• Jaafar, Badamasi
• SabonGari, Nahuru Ado
• Yakubu, Ismail Zahraddeen

Titel

Deep Learning for Detecting Ransomware in Edge Computing Devices Based On Autoencoder Classifier

Ist Teil von

• 2019 4th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT), 2019, p.240-243

Ort / Verlag

IEEE

Erscheinungsjahr

2019

Quelle

IEEE Xplore

Beschreibungen/Notizen

• Edge computing has been of most advantage to the new promising emergent paradigm, Internet of Things, allowing data and applications to be processed and stored at the edge of the network than to the cloud hence reducing the latency of transmission data. Edge computing devices are faced with security challenges. Ransomware has become a significant global threat with the ransomware-as-a-service model enabling easy availability and deployment, and the potential for high revenues creating a viable criminal business model. Although machine learning algorithms are already been used to detect ransomware, featuring engineering process is mostly tedious, time consuming and more so inefficient and biased features are mostly extracted. In this paper, we proposed a deep learning method which eliminates feature engineering, the method is used in the classification of ransomware. We obtained a 99.7% true positive rate indicating that our classifier is the best.