• Login
    View Item 
    •   SMARTech Home
    • Institute for Information Security & Privacy (IISP)
    • Institute for Information Security & Privacy Cybersecurity Lecture Series
    • View Item
    •   SMARTech Home
    • Institute for Information Security & Privacy (IISP)
    • Institute for Information Security & Privacy Cybersecurity Lecture Series
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Adversarial Attack on Graph-Structured Data

    Thumbnail
    View/Open
    dai.mp4 (303.9Mb)
    dai_videostream.html (1.013Kb)
    transcript.txt (4.206Kb)
    thumbnail.jpg (121.4Kb)
    Date
    2019-03-15
    Author
    Dai, Hanjun
    Metadata
    Show full item record
    Abstract
    Deep learning on graph structures has shown exciting results in cybersecurity applications, such as risk management, binary code similarity detection, etc. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool deep learning models by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. We further propose attack methods based on genetic algorithms and gradient descent in the scenario where additional prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers.
    URI
    http://hdl.handle.net/1853/60962
    Collections
    • Institute for Information Security & Privacy Cybersecurity Lecture Series [118]

    Browse

    All of SMARTechCommunities & CollectionsDatesAuthorsTitlesSubjectsTypesThis CollectionDatesAuthorsTitlesSubjectsTypes

    My SMARTech

    Login

    Statistics

    View Usage StatisticsView Google Analytics Statistics
    • About
    • Terms of Use
    • Contact Us
    • Emergency Information
    • Legal & Privacy Information
    • Accessibility
    • Accountability
    • Accreditation
    • Employment
    • Login
    Georgia Tech

    © Georgia Institute of Technology

    • About
    • Terms of Use
    • Contact Us
    • Emergency Information
    • Legal & Privacy Information
    • Accessibility
    • Accountability
    • Accreditation
    • Employment
    • Login
    Georgia Tech

    © Georgia Institute of Technology