A Digital DNA Sequencing Engine for Ransomware Detection Using Machine Learning

Firoz Khan, Cornelius Ncube, Lakshmana Kumar Ramasamy, Seifedine Kadry, Yunyoung Nam

IEEE Access · 2020 · 105 citations · 19 references

DOIFull text

Open access

Concepts

TL;DR

Malware, including ransomware that encrypts victim data for ransom, employs diverse techniques such as machine learning to evade detection, highlighting the need to understand these strategies for effective countermeasures. This study introduces DNAact‑Ran, a digital DNA sequencing engine that applies machine learning to detect ransomware. DNAact‑Ran employs digital DNA sequencing constraints and k‑mer frequency vectors, and its performance was evaluated on 582 ransomware and 942 goodware samples using precision, recall, F‑measure, and accuracy metrics. The evaluation shows DNAact‑Ran accurately and effectively detects ransomware, outperforming existing methods.

Abstract

Malware is `malicious software' programs that carry out many of the cyberattacks on the Internet, including cybercrime, fraud, scams and nation-state cyberwar. These malicious software programs come in a wide range of different classifications such as viruses, Trojans, worms, spyware, botnet malware, ransomware, Rootkit, etc. Ransomware is class of malware that holds the victim's data hostage by encrypting the data on a user's computer to make it unavailable to the user and only decrypt it after the user pays a ransom in the form of a sum of money. To avoid detection, different variants of ransomware utilise one or more techniques in their attack flow including Machine Learning (ML) algorithms. There is, therefore, a need to understand the techniques used ransomware development and their deployment strategy in order to understand their attack flow better to develop appropriate countermeasures. In this paper, we propose DNAact-Ran, A Digital DNA Sequencing Engine for Ransomware Detection Using Machine Learning. DNAact-Ran utilises Digital DNA sequencing design constraints and k-mer frequency vector. To measure the efficacy of the proposed approach, we evaluated DNAact-Run on 582 ransomware and 942 goodware instances to measure the performance of precision, recall, f-measure and accuracy. Compared to other methods, the evaluation results show that DNAact-Run can predict and detect ransomware accurately and effectively.

References

19