Examining the Security of DDoS Detection Systems in Software Defined Networks
Examining the Security of DDoS Detection Systems in Software Defined Networks
复制标题
检查软件定义网络中 DDoS 检测系统的安全性
DOI：
10.1145/3360468.3368174
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Mohaisen, Aziz
中科院分区：
文献类型：
--
作者：
Abusnaina, Ahmed;Nyang, DaeHun;Yuksel, Murat;Mohaisen, Aziz
随着SDN（Software-Defined Networking，软件定义网络）倡导集中式网络视图的快速发展，需要高效可靠的分布式拒绝服务（Distributed Denial of Service，DDoS）防御来保护集中式SDN控制器。在这项工作中，我们探索了SDN中基于DL的DDoS防御对对抗性学习攻击的鲁棒性。首先，我们研究了通用的现成的对抗性攻击，以测试SDN中DDoS防御的鲁棒性。然后，我们提出了流合并的现实对抗流，同时实现了高规避率。评估结果表明，所提出的流合并是能够迫使基于DL的DDoS防御错误分类100%的良性流量为恶意。
With the rapid development of Software-Defined Networking (SDN) advocating a centralized view of networks, efficient and reliable Distributed Denial of Service (DDoS) defenses are necessary to protect the centralized SDN controller. In this work, we explore the robustness of DL-based DDoS defenses in SDN against adversarial learning attacks. First, we investigate generic off-the-shelf adversarial attacks to test the robustness of DDoS defenses in SDN. Then, we propose Flow-Merge for realistic adversarial flows while achieving a high evasion rate. The evaluation shows that the proposed Flow-Merge is able to force the DL-based DDoS defenses to misclassify 100% of benign flows as malicious.
DOI：
10.1109/icdcs.2019.00130
发表时间：
2019-07
期刊：
2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS)
影响因子：
--
作者：
Ahmed A. Abusnaina;Aminollah Khormali;Hisham Alasmary;Jeman Park;Afsah Anwar;Aziz Mohaisen
通讯作者：
Ahmed A. Abusnaina;Aminollah Khormali;Hisham Alasmary;Jeman Park;Afsah Anwar;Aziz Mohaisen
DOI：
10.1109/dsc47296.2019.8937669
发表时间：
2019-11
期刊：
2019 IEEE Conference on Dependable and Secure Computing (DSC)
影响因子：
--
作者：
Ahmed A. Abusnaina;Aminollah Khormali;Daehun Nyang;M. Yuksel;Aziz Mohaisen
通讯作者：
Ahmed A. Abusnaina;Aminollah Khormali;Daehun Nyang;M. Yuksel;Aziz Mohaisen