The Applications of Deep Learning on Traffic Identification

Presented at Black Hat USA 2015, Aug. 6, 2015, 9 a.m. (25 minutes)

Generally speaking, most systems of network traffic identification are based on features. The features may be port numbers, static signatures, statistic characteristics, and so on. The difficulty of the traffic identification is to find the features in the flow data. The process is very time-consuming. Also, these approaches are invalid to unknown protocol. To solve these problems, we propose a method that is based on neural network and deep learning a hotspot of research in machine learning. The results show that our approach works very well on the applications of feature learning, protocol identification, and anomalous protocol detection.

Presenters:

• Bo Liu - Qihoo 360 Technology Co., Ltd
  Bo Liu is a machine learning & data mining researcher.
• Zhuo Zhang - Qihoo 360 Technology Co., Ltd
  Zhuo Zhang is a team leader with an lab focusing on "Data driven sercurity" in Qihoo360. His team uses big data analytics to find out the threat in the enterprises .He devotes to developing the deep learning system and doing security data research. Until now,his team finds out many threats in the enterprises in China.
• Chuanming Huang - Qihoo 360 Technology Co., Ltd
  Chuanming Huang is a tech enthusiast, interested in various data mining and parallel computing techniques.
• Zhanyi Wang - Qihoo 360 Technology Co. Ltd.
  Zhanyi Wang is a data mining researcher with a passion for information security. He hopes to use his experiences in machine learning and data mining to solve problems within this field.

Links:

• https://www.blackhat.com/us-15/briefings.html#the-applications-of-deep-learning-on-traffic-identification
• https://infocon.org/cons/Black Hat/Black Hat USA/Black Hat USA 2015/video/Black Hat USA 2015 - The Applications Of Deep Learning On Traffic Identification.srt (subtitles)
• https://infocon.org/cons/Black Hat/Black Hat USA/Black Hat USA 2015/video/Black Hat USA 2015 - The Applications Of Deep Learning On Traffic Identification.mp4
• https://www.youtube.com/watch?v=yZ-Y1WCM0lc
• https://www.blackhat.com/docs/us-15/materials/us-15-Wang-The-Applications-Of-Deep-Learning-On-Traffic-Identification.pdf
• https://www.blackhat.com/docs/us-15/materials/us-15-Wang-The-Applications-Of-Deep-Learning-On-Traffic-Identification-wp.pdf

Similar Presentations:

• DEF CON 24 (2016) / Machine Duping 101: Pwning Deep Learning Systems
• Kernelcon 2019 / PCAP Feature Engineering for Machine Learning
• DeepSec 2016 „Ten“ / Machine Duping: Pwning Deep Learning Systems