Author: Peiser, Stefan Carl; Friborg, Ludwig; Scandariato, Riccardo
Title: JavaScript Malware Detection Using Locality Sensitive Hashing Cord-id: uq71g1vc Document date: 2020_8_1
ID: uq71g1vc
Snippet: In this paper, we explore the idea of using locality sensitive hashes as input features to a feed-forward neural network with the goal of detecting JavaScript malware through static analysis. An experiment is conducted using a dataset containing 1.5M evenly distributed benign and malicious samples provided by the anti-malware company Cyren. Four different locality sensitive hashing algorithms are tested and evaluated: Nilsimsa, ssdeep, TLSH, and SDHASH. The results show a high prediction accurac
Document: In this paper, we explore the idea of using locality sensitive hashes as input features to a feed-forward neural network with the goal of detecting JavaScript malware through static analysis. An experiment is conducted using a dataset containing 1.5M evenly distributed benign and malicious samples provided by the anti-malware company Cyren. Four different locality sensitive hashing algorithms are tested and evaluated: Nilsimsa, ssdeep, TLSH, and SDHASH. The results show a high prediction accuracy, as well as low false positive and negative rates. These results show that LSH based neural networks are a competitive option against other state-of-the-art JavaScript malware classification solutions.
Search related documents:
Co phrase search for related documents- accurate understanding and machine model: 1
Co phrase search for related documents, hyperlinks ordered by date