| Title | Adversarial Attack against LSTM-Based DDoS Intrusion Detection System |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Huang, Weiqing, Peng, Xiao, Shi, Zhixin, Ma, Yuru |
| Conference Name | 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI) |
| Date Published | Nov. 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-9228-4 |
| Keywords | adversarial samples, composability, Computer crime, DDoS attack detection, DDoS detector, Detectors, genetic algorithm, genetic algorithms, Human Behavior, Intrusion detection, LSTM, machine learning, machine learning algorithms, Metrics, probability weighted, pubcrawl, resilience, Resiliency, Tools |
| Abstract | Nowadays, machine learning is a popular method for DDoS detection. However, machine learning algorithms are very vulnerable under the attacks of adversarial samples. Up to now, multiple methods of generating adversarial samples have been proposed. However, they cannot be applied to LSTM-based DDoS detection directly because of the discrete property and the utility requirement of its input samples. In this paper, we propose two methods to generate DDoS adversarial samples, named Genetic Attack (GA) and Probability Weighted Packet Saliency Attack (PWPSA) respectively. Both methods modify original input sample by inserting or replacing partial packets. In GA, we evolve a set of modified samples with genetic algorithm and find the evasive variant from it. In PWPSA, we modify original sample iteratively and use the position saliency as well as the packet score to determine insertion or replacement order at each step. Experimental results on CICIDS2017 dataset show that both methods can bypass DDoS detectors with high success rate. |
| URL | https://ieeexplore.ieee.org/document/9288358 |
| DOI | 10.1109/ICTAI50040.2020.00110 |
| Citation Key | huang_adversarial_2020 |
Adversarial Attack against LSTM-Based DDoS Intrusion Detection System