Corpus ID: 212506602

CYBER ATTACK DETECTION IN REMOTE TERMINAL UNIT OF SCADA SYSTEMS

@inproceedings{Dakheel2019CYBERAD,
  title={CYBER ATTACK DETECTION IN REMOTE TERMINAL UNIT OF SCADA SYSTEMS},
  author={Ali Hasan Dakheel and O. Ucan and O. Bayat and Hamzah Hameed Jasim},
  year={2019}
}
Supervisory Control and Data Acquisition (SCADA) systems are widely used in critical infrastructures such as water distribution networks, electricity generation and distribution plants, oil refineries, nuclear plants, and public transportation systems. Every communication is done through encrypted messages to protect the pipeline from any intrusion from outside, it is almost impossible to interpret the observed payload. SCADA systems typically do require a high throughput but are much more… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 18 REFERENCES
Intrusion detection using deep belief networks
With the advent of digital technology, security threats for computer networks have increased dramatically over the last decade being much bolder and brazen. There is a great need for an effectiveExpand
Scalable architecture for online prioritisation of cyber threats
TLDR
A novel online approach that monitors the behaviour of each internal host, detects suspicious activities possibly related to advanced attacks, and correlates these anomaly indicators to produce a list of the most likely compromised hosts to pave the way to novel forms of detection of advanced malware. Expand
An analysis of Recurrent Neural Networks for Botnet detection behavior
A Botnet can be conceived as a group of compromised computers which can be controlled remotely to execute coordinated attacks or commit fraudulent acts. The fact that Botnets keep continuouslyExpand
An efficient flow-based botnet detection using supervised machine learning
  • M. Stevanovic, J. Pedersen
  • Computer Science
  • 2014 International Conference on Computing, Networking and Communications (ICNC)
  • 2014
TLDR
A novel flow-based detection system that relies on supervised machine learning for identifying botnet network traffic and shows that in order to achieve accurate detection traffic flows need to be monitored for only a limited time period and number of packets per flow. Expand
Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection
TLDR
This paper applies Long Short Term Memory (LSTM) architecture to a Recurrent Neural Network (RNN) and train the IDS model using KDD Cup 1999 dataset and confirms that the deep learning approach is effective for IDS. Expand
Malware classification with recurrent networks
TLDR
This work proposes a different approach, which, similar to natural language modeling, learns the language of malware spoken through the executed instructions and extracts robust, time domain features. Expand
Deep Learning Based Cryptographic Primitive Classification
TLDR
A novel approach for the classification of cryptographic primitives in compiled binary executables using deep learning is presented, utilising core primitives from OpenSSL with multivariate obfuscation for a vastly scalable distribution. Expand
Efficient and Secure Source Authentication for Multicast
TLDR
This paper proposes several substantial modifications and improvements to TESLA, which allows receivers to authenticate most packets as soon as they arrive, and improves the scalability of the scheme, reduce the space overhead for multiple instances, increase its resistance to denial-of-service attacks, and more. Expand
DL 4 MD : A Deep Learning Framework for Intelligent Malware Detection
In the Internet-age, malware poses a serious and evolving threat to security, making the detection of malware of utmost concern. Many research efforts have been conducted on intelligent malwareExpand
Large-scale malware classification using random projections and neural networks
TLDR
This work uses random projections to further reduce the dimensionality of the original input space and trains several very large-scale neural network systems with over 2.6 million labeled samples thereby achieving classification results with a two-class error rate of 0.49% for a single neural network and 0.42% for an ensemble of neural networks. Expand
...
1
2
...