Loading...

Hardware Acceleration of Deep Learning based Firewalls Using FPGA

Fotovat, Amin | 2019

370 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52643 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jahangir, Amir Hossein
  7. Abstract:
  8. In recent years, due to the drawback of rule-based firewalls in detecting unknown attacks, using neural networks has got more attention to be used in firewalls. As the computation load of neural networks are so much there is a need to decrease the processing time and power consumption as they are under load 24/7. Although there have been huge achievements in the usage of graphics processing units (which contain numerous processing cores) in neural networks, their high power consumption has made the scientists think about an alternative to implement neural networks. Field Programmable Gate Array (FPGA) is one of the most serious candidates to be used for implementing neural networks. The goal of this project is to implement a neural network-based firewall on the FPGA. This is the first time the PYNQ from Xilinx is used for this purpose. PYNQ is run on the ARM processor of the board and simplifies the FPGA-independent processes. The vendor of this platform does not officially support the ZC706 (the available board). Hence, in a side project, PYNQ was built on this board. To assess the output of the project, some famous penetration test tools like sqlmap and OWASP ZAP were used. Also, the firewall was tested with the Spirent N11U and its attack database. Moreover, the power consumption of the FPGA chip is 1.05W while the power consumption of the board is 30W. The average response time of each request is 37 ms. Combining the neural network-based firewalls, which are by themselves state-of-the-art in the field of cybersecurity, and the FPGA devices, can open the door to produce new-generation network security devices
  9. Keywords:
  10. Neural Networks ; Firewall ; Field Programmable Gate Array (FPGA) ; Hardware Accelerator ; Deep Learning

 Digital Object List

 Bookmark

No TOC