Abstract | ||
---|---|---|
The amount of Internet traffic is ever increasing. With a well maintained network infrastructure, people find their way to Internet forums, video streaming services, social media and webshops on a day-to-day basis. With the growth of the online world, criminal activities have also spread out to the Internet. Security researchers and system administrators develop and maintain infrastructures to control these possible threats. This work focuses on one aspect of network security: intrusion detection. An Intrusion Detection System (IDS) is only one of the many components in the security engineer's toolbox. An IDS is a passive component that tries to detect malicious activities. With the increase of Internet traffic and bandwidth, the detection speed of IDSs needs to be improved accordingly. This work focuses on how Field-programmable Gate Arrays (FPGA) are used as hardware accelerators to assist the IDS in keeping up with high network speed. We give an overview of three approaches: Intrusion detection based on machine learning, pattern matching, and large flow detection. This work is concluded with a comparison between the three approaches on the most relevant metrics. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-95085-9_13 | SECURITY, PRIVACY, AND APPLIED CRYPTOGRAPHY ENGINEERING, SPACE 2021 |
Keywords | DocType | Volume |
Network intrusion detection, Deep learning, FPGA | Conference | 13162 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurens Le Jeune | 1 | 0 | 0.34 |
Arish Sateesan | 2 | 0 | 0.34 |
Md Masoom Rabbani | 3 | 0 | 0.34 |
Toon Goedemé | 4 | 0 | 0.34 |
Jo Vliegen | 5 | 0 | 0.34 |
Nele Mentens | 6 | 394 | 47.72 |