Cybersecurity

Method developed to detect cyber attacks with compressed network traffic

Researchers at the U.S. Army Research Laboratory (ARL) and Towson University are developing a method on compressing network traffic as much as possible without losing the ability to detect and investigate malicious activity.
By Gregory Hale May 25, 2019
Scientists at the Army Research Lab (ARL) and Towson University may have identified a way to improve the cybersecurity of distributed network intrusion detection. Courtesy: U.S. Army Illustration/ISSSource

Government and businesses are spending more time and money finding ways to defend against attacks as cybersecurity becomes one of the nation’s top concerns. However, there might be a way to improve network security.

Cybersecurity systems use distributed network intrusion detection that allows a small number of trained analysts to monitor several networks at the same time, reducing cost through economies of scale and more efficiently leveraging limited cybersecurity expertise; however, this approach requires data be transmitted from network intrusion detection sensors on the defended network to central analysis severs. Transmitting all of the data captured by sensors requires too much bandwidth, researchers said.

Because of this, most distributed network intrusion detection systems only send alerts or summaries of activities back to the security analyst. With only summaries, cyber attacks can go undetected because the analyst did not have enough information to understand the network activity, or time may be wasted chasing down false positives.

In a presentation at the 10th International Multi-Conference on Complexity, Informatics and Cybernetics, researchers at the U.S. Army Combat Capabilities Development Command’s Army Research Laboratory (ARL), the Army’s corporate research laboratory, and Towson University wanted to identify how to compress network traffic as much as possible without losing the ability to detect and investigate malicious activity.

Working on the theory malicious network activity would manifest its maliciousness early, the researchers developed a tool designed to stop transmitting traffic after a given number of messages had be transmitted. The resulting compressed network traffic was analyzed and compared to the analysis performed on the original network traffic.

As suspected, researchers found cyber attacks often do manifest maliciousness early in the transmission process. When the team identified malicious activity later in the transmission process, it was often not the first occurrence of malicious activity in the network flow.

“This strategy should be effective in reducing the amount of network traffic sent from the sensor to central analyst system,” said Sidney Smith, an ARL researcher. “Ultimately, this strategy could be used to increase the reliability and security of Army networks.”

For the next phase, researchers want to integrate this technique with network classification and lossless compression techniques to reduce the amount of traffic that needs to be transmitted to the central analysis systems to less than 10% of the original traffic volume while losing no more than 1% of cyber security alerts.

“The future of intrusion detection is in machine learning and other artificial intelligence techniques,” Smith said. “However, many of these techniques are too resource intensive to run on the remote sensors, and all of them require large amounts of data. A cybersecurity system incorporating our research technique will allow the data most likely to be malicious to be gathered for further analysis.”

This content originally appeared on ISSSource.com. ISSSource is a CFE Media content partner. Edited by Chris Vavra, production editor, CFE Media, cvavra@cfemedia.com.


Gregory Hale
Author Bio: Gregory Hale is the editor and founder of Industrial Safety and Security Source (ISSSource.com), a news and information website covering safety and security issues in the manufacturing automation sector.