Deep learning approach for cyberattack detection
Yiyun Zhou, Meng Han, Liyuan Liu et al. · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · 2018
With the accelerated growth of internet of things IoT application in recent years, cities have become smarter to optimize resource and improved the quality of life for residents. On the other hand, the IoT face the severe security problem like confidentiality, integrity, privacy, and availability. To prevent the cyberattack irreversible damage, we propose a framework, called DFEL, to detect the internet intrusion in the IoT environment. Through the experimental results, authors present that DFEL not only boosts classifiers' accuracy to predict cyberattack but also significantly reduce the detection time. Furthermore, the paper demonstrates how the DFEL balance the detection performance and speed.
Cited by 102 works. doi:10.1109/infcomw.2018.8407032
Authors
References
- Reducing the Dimensionality of Data with Neural Networks
- Dropout: a simple way to prevent neural networks from overfitting
- Representation Learning: A Review and New Perspectives
- A detailed analysis of the KDD CUP 99 data set
- UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)
- Deep learning applications and challenges in big data analytics
- Transfer Learning for Visual Categorization: A Survey
- A new approach to intrusion detection using Artificial Neural Networks and fuzzy clustering
- Transfer learning using computational intelligence: A survey
- Dendron : Genetic trees driven rule induction for network intrusion detection systems