Name
Abstract | ||
|---|---|---|
The expected high bandwidth of 5G and the envisioned massive number of connected devices will open the door to increased and sophisticated attacks, such as application-layer DDoS attacks. Application-layer DDoS attacks are complex to detect and mitigate due to their stealthy nature and their ability to mimic genuine behavior. In this work, we propose a robust application-layer DDoS self-protection framework that empowers a fully autonomous detection and mitigation of the application-layer DDoS attacks leveraging on Deep Learning (DL) and SDN enablers. The DL models have been proven vulnerable to adversarial attacks, which aim to fool the DL model into taking wrong decisions. To overcome this issue, we build a DL-based application-layer DDoS detection model that is robust to adversarial examples. The performance results show the effectiveness of the proposed framework in protecting against application-layer DDoS attacks even in the presence of adversarial attacks. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/WCNC45663.2020.9120472 | 2020 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC) |
DocType | ISSN | Citations |
Conference | 1525-3511 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chafika Benzaid | 1 | 54 | 13.06 |
| Mohammed Boukhalfa | 2 | 0 | 0.34 |
| Tarik Taleb | 3 | 3111 | 237.91 |