Daniel Balasubramanian lands $6.89 million DARPA grant to train cyber agents against attacks

Daniel Balasubramanian, a senior research scientist at Vanderbilt’s Institute for Software Integrated Systems, is set to lead a $6.89 million, four-year grant from the Defense Advanced Research Projects Agency (DARPA). The objective is to create realistic network environments that will be utilized to train cyber agents in countering advanced and persistent cyber threats.

Global cybercrime costs are projected to reach as high as $9.5 trillion in 2024, according to Cybersecurity Ventures. A single data breach can incur costs in the millions of dollars. As cyberattacks increase in scale and complexity, there is a growing need for network operators to comprehend and defend against these threats in real time.

Balasubramanian emphasized the economic and national security benefits of mitigating cyber attacks, stating, “Anything we can do to reduce and lessen the severity of such attacks has a huge economic benefit. Beyond the financial impact, safeguarding these networks is crucial to our national security.”

The DARPA grant, titled "Reinforcement Against Malicious Penetration by Adversaries in Realistic Topologies (RAMPART)," is a collaborative effort involving a Vanderbilt team at ISIS and partners: Jack W. Davidson, a network security expert and computer science professor at the University of Virginia, and Paul Roysdon, chief solutions architect of artificial intelligence and machine learning at Leidos.

The primary objective is to develop a cutting-edge learning environment where teams can learn to defend against incoming attacks and identify system vulnerabilities. Balasubramanian explained, “Our approach to training cyber agents uses a combination of model-based representations and deep reinforcement learning (RL) to develop autonomous agents that are capable of defending a network against attacks. Augmenting human operators with automated agents will be crucial to defending against the next generation of cyberattacks.”

Read the full details here.