Overview
Explore a cutting-edge approach to malware traffic detection using deep learning techniques without relying on expert knowledge. This 25-minute IEEE conference talk, presented at the 2nd Deep Learning and Security Workshop during the 2019 IEEE Symposium on Security & Privacy, delves into the application of deep learning models for network security. Learn how these models can effectively detect and classify malicious network traffic by analyzing raw measurements directly from monitored byte streams. Discover the advantages of this method over traditional shallow models that require handcrafted features, and understand how deep learning can better capture the underlying statistics of malicious traffic. Gain insights into different raw-traffic feature representations, including packet and flow-level ones, and their impact on detection performance. Understand the potential of this approach to revolutionize network security systems and improve their robustness against evolving networking attacks.
Syllabus
Deep in the Dark - Deep Learning-based Malware Traffic Detection without Expert Knowledge
Taught by
IEEE Symposium on Security and Privacy