We present our work on evaluating the usefulness of deep, convolutional neural networks (DNN) for classifying assembly or machine code as malicious or benign. Our results show that a DNN trained on a small dataset showed 95.1% accuracy in program classification. We also show a modified network can achieve 88% accuracy in classifying nine types of malware on a larger dataset, leaving room for future work to address variable length files.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting Malicious Assembly with Deep Learning


    Contributors:
    Santacroce, M. (author) / Koranek, Daniel (author) / Kapp, David (author) / Ralescu, Anca (author) / Jha, R. (author)


    Publication date :

    2018-07-01


    Size :

    103816 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    SYSTEM AND PROCESSES FOR DETECTING MALICIOUS HARDWARE

    KAMIR EYAL / FOK ALEXANDER / TUCHMAN YANIV et al. | European Patent Office | 2020

    Free access

    A Machine Learning Approach for Detecting Malicious Websites using URL Features

    Manjeri, Akshay Sushena / R, Kaushik / MNV, Ajay et al. | IEEE | 2019


    System and processes for detecting malicious hardware

    KAMIR EYAL / FOK ALEXANDER / TUCHMAN YANIV et al. | European Patent Office | 2021

    Free access