Abstract | ||
---|---|---|
Deep learning methods, e.g., convolutional neural networks(CNNs) and Recurrent Neural Networks(RNNs), have achieved great success in image processing and natural language processing especially in high level vision applications such as recognition and understanding. However, it is rarely used to solve information security problems such as attack detection studied in this paper. Here, we move forward a step and propose a novel intelligent attack detection method based on long short term memory recurrent neural networks (LSTM-RNNs). To achieve high detection rate, data preprocessing, feature abstraction, training and detection are seamlessly integrated into an end-to-end detection framework. Data preprocessing provides high-quality data for subsequent processing, then different types of features are extracted from the processed data. RNN is used to generate classifiers by training neural networks with different types of features, which preserve attack features of input vectors and classify the attack from normal data. Experimental results validate that the proposed attack detection method greatly outperforms several attack detection methods that use feature detection and Bayesian or SVM classifiers. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/DSC.2018.00078 | 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC) |
Keywords | Field | DocType |
Deep learning,attack detection,data security,sustainable computing,recurrent neural networks (RNNs) | Pattern recognition,Convolutional neural network,Computer science,Support vector machine,Recurrent neural network,Data pre-processing,Feature extraction,Artificial intelligence,Deep learning,Artificial neural network,Intrusion detection system | Conference |
ISBN | Citations | PageRank |
978-1-5386-4211-5 | 2 | 0.38 |
References | Authors | |
13 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yunsheng Fu | 1 | 27 | 2.99 |
Fang Lou | 2 | 17 | 3.07 |
Fangzhi Meng | 3 | 2 | 0.38 |
Zhi-Hong Tian | 4 | 312 | 52.75 |
Hua Zhang | 5 | 328 | 13.64 |
Feng Jiang | 6 | 304 | 37.75 |