Autoencoder-based feature learning for cyber security applications

By Mahmood Yousefi-Azar, V. Varadharajan, Len Hamey, U. Tupakula. IEEE International Joint Conference on Neural Network, 2017

300 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/85dacb2fa8093e2d8a792c6f53c3429cbbdf5606

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey (2023, methodology): “For example, NIDS designed for IoT networks are evaluated with General network datasets [39], [48], [49], [53], and a large majority of recently proposed NIDS [39], [40], [41], [43], [46], [48], [49], [50] are evaluated with NSL-KDD and KDD Cup’99 only, which is over 20 years old and are not represe”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “An improved stacked AE is employed in [232], where Li et al. incorporate Bayesian methods into AEs to enhance the inference accuracy in network traffic classification.”
A Survey of Deep Learning Methods for Cyber Security (2019, methodology): “[103] 11 Intrusion Detection Malware Detection NSL-KDD [58], Microsoft Malware Classification Challenge [70]”
Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection (2018, methodology): “In [10], a feature learning model based on AE was presented to achieve a good representation of different feature sets.”
A Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges (2020, background): “AEs are extensively used for IoT system security and devices [161].”
Enhanced Network Anomaly Detection Based on Deep Neural Networks (2018, methodology): “This approach was also adopted by [16]–[18].”
Microsoft Malware Classification Challenge (2018, background): “[52] Feature Engineering Jun 2017 Kebede et al.”
A Review of Intrusion Detection Systems Using Machine and Deep Learning in Internet of Things: Challenges, Solutions and Future Directions (2020, methodology): “Some researches [116–118] have used KNN based classification for anomaly and intrusion detection in general and IoT based network intrusion detection in particular [119,120] with reasonable accuracy in detecting User to Root (U2R) and Remote to Local (R2L) attacks.”
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection (2018, background): “In [22] and [23], the authors propose the use of autoencoders to extract features from datasets in order to improve the detection of cyber threats.”
Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges (2017, methodology): “…were used as a generative model and were trained in a way that the bottleneck layer learnt a latent representation of the feature set; these features were then used for malware classiﬁcation and anomaly detection to produce results that improved the state of the art in feature selection [24].”
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security (2018, methodology): “In this subsection, we discuss the common ML algorithms (i.e. decision trees (DT), support vector machines (SVM), Bayesian algorithms, k-nearest neighbour (KNN), random forest (RF), association rule (AR) algorithms, ensemble learning, k-means clustering and principal component analysis (PCA)) and th”