Early detection of Crossfire attacks using deep learning
Halls department, Hall 3
Thursday, 28 December 2017
10:00 - 11:00
Crossfire attack is a recently proposed threat designed to disconnect whole geographical areas, such as cities or states, from the Internet. Orchestrated in multiple phases, the attack uses a massively distributed botnet to generate low-rate benign traffic aiming to congest selected network links, so-called target links. The adoption of benign traffic, while simultaneously targeting multiple network links, makes the detection of the Crossfire attack a serious challenge. In this paper, we propose a framework for early detection of Crossfire attack, i.e., detection in the warm-up period of the attack. We propose to monitor traffic at the potential decoy servers and discuss the advantages comparing with other monitoring approaches. Since the low-rate attack traffic is very difficult to distinguish from the background traffic, we investigate several deep learning methods to mine the spatiotemporal features for attack detection. We investigate Auto-encoder, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network to detect the Crossfire attack during its warm-up period. We report encouraging experiment results.
Mostafa Rezazad received his undergraduate degree in computer engineering from Azad University at Central Tehran in 2000. After working as a network administrator for a couple of years, he went back to school and received his Masters in Computer Architecture under the supervision of Professor Sarbazi-Azad in 2004 from Sharif University of Technology. From the beginning of his course, he worked at IBM as a research assistant. He started his own start-up after graduation and continued his collaboration with the research group in IPM at the same time. Then he moved to Malaysia and worked as a consultant at Fuziq Co. Kuala-Lumpur in 2009. In 2010 he was admitted into NUS as a Ph.D. student under advisory of Prof. Y.C. Tay. He received his Ph.D. in 2015 and is doing Postdoc at Singapore University of Technology and Design since then.