This is a notice for site visitors.

The Latest

Industry News: Researchers Say Machine Learning Boosts Defense Against Multi-Stage Cyber Attacks

Researchers Say Machine Learning Boosts Defense Against Multi-Stage Cyber Attacks

February 8, 2021

A machine learning algorithm may give organizations a powerful and cost-effective tool for defending against attacks on vulnerable computer networks and cyber-infrastructure, often called zero-day attacks, according to researchers.

These zero-day attacks can quickly overwhelm traditional defenses, resulting in billions of dollars of damage and requiring weeks of manual patching work to shore up the systems after the intrusion. Typical responses to an attack can take up to 15 days., the researchers found.

The Penn State-led team of researchers has created an automatically adaptive cyber defense against these attacks using a machine learning approach that is based on a technique known as reinforcement learning.

The team developed this machine learning-driven method to address what it saw as current limitations in a method to detect and respond to cyber-attacks called moving target defense, or MTD, according to Minghui Zhu, associate professor of electrical engineering and computer science and Institute for Computational and Data Sciences co-hire.

“These adaptive manual target-defense techniques can dynamically and proactively reconfigure deployed defenses that can increase uncertainty and complexity for attackers during vulnerability windows,” said Zhu. “However, existing MTD techniques suffer from two limitations. First, manual selection can be very time consuming. Secondly, manually selected configurations might not be the most cost-effective method to handle this.”

Responses that take days can use up significant funds and resources for an organization, according to the researchers, who released their findings in the ACM Transactions on Privacy and Security.

Zhu said that zero-day attacks are among the most dangerous threats to computer systems and can cause serious and lasting damage. As an example, the WannaCry ransomware attack, which occurred in May 2017, targeted more than 200,000 Windows computers across 150 countries, and caused an estimated $4 billion to $8 billion worth of damage.

The team’s approach relies on reinforcement learning, which is a way that a decision maker can learn to make the right choices by selecting actions that can maximize rewards by balancing exploitation — leveraging past experiences — and exploration — trying new actions, according to Peng Liu, the Raymond G. Tronzo, MD Professor of Cybersecurity in the College of Information Sciences and Technology.

 

 

“The decision maker learns optimal policies or actions through continuous interactions with an underlying environment, which is partially unknown,” said Liu. “So, reinforcement learning is particularly well-suited to defend against zero-day attacks when critical information — the targets of the attacks and the locations of the vulnerabilities — is not available.”

The researchers tested their reinforcement learning algorithm in a 10-machine network. They decided that although a 10-computer network may not seem very large, it is actually more than robust enough for the test. The setup also included web and mail servers, a Gateway server, SQL server, DNS server and admin server. They installed a firewall to prevent access to the internal hosts. They also selected vulnerabilities that could produce multiple attack scenarios for the test.

The researchers acknowledge there is room for further improvement in their approach. For example, their algorithm relies on model-free reinforcement learning, which requires a large amount of data or a large number of iterations to learn a relatively good defense policy. In the future they would like to incorporate model-based approaches to accelerate the learning process.

Zhu and Liu also worked with Zhisheng Hu, former doctoral student at electrical engineering and computer science, and now senior security scientist of Baidu Security at Silicon Valley; Jun Xu, former doctoral student in information sciences and technology, and now assistant professor, Stevens Institute of Technology; and Ping Chen, former post-doctoral scholar in information sciences and technology, and now staff security architect of JD.com American Technologies.
v
The Department of Defense Multidisciplinary University Research Initiative (MURI) award supported the work.

Study: Adaptive Cyber Defense Against Multi-Stage Attacks Using Learning-Based POMDP

Share this article