Recent literature work has shown that many machine learning models are vulnerable to adversarial attacks, but there also exist techniques that can be used to improve their robustness. Here, we apply some adversarial attack methods for the purpose of generating adversarial features. The said adversarial attacks are directed towards a neural network that is initially trained to classify malware programs in the labeled subset of the BIG 2015 dataset based on the malware's re-sampled and resized HEX codes, which thereby constitute the aforementioned features. Furthermore, via adversarial training, we investigate the creation of a more robust neural network.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Investigating the Generation of Adversarial Malware Features and the Use of Adversarial Training




    Publication date :

    2021-08-16


    Size :

    1691251 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation

    Khan, Salman H. / Hayat, Munawar / Barnes, Nick | ArXiv | 2018

    Free access

    A Search for Visual Features in Adversarial Networks

    Dehghani, Farzaneh / Ghorban, Farzin / Velten, Joerg et al. | VDE-Verlag | 2020


    Graph generation by a generative adversarial network

    PRONOVOST ETHAN MILLER | European Patent Office | 2025

    Free access

    Adversarial training is not ready for robot learning

    Lechner, Mathias / Hasani, Ramin / Grosu, Radu et al. | BASE | 2021

    Free access

    Vehicle Trajectory Generation Based on Generation Adversarial Network

    Zhonghe He / Renchi Shao / Sijia Xiang | DOAJ | 2024

    Free access