Common cyber defense tools don't detect an intrusion until 200 days after it occurs. Now more than ever, cyber attacks are a main concern for large enterprises—from the federal government to Fortune 500 companies—and adversaries are getting smarter and faster every day.
The old way of reactively defending against cyber attacks is no longer working. Human-driven defense is too slow to keep up with technologically advanced adversaries and there's a shortage of cyber talent available to keep up with demand. Current artificial intelligence (AI)-driven defense products create numerous false positives, creating a backlog of alerts and resulting in significant time loss as analysts pore through the data to find no threat at all. Cybersecurity experts face the challenge of building an adaptable solution that can learn the norms of a given network while rapidly evolving in defense of new attack structures. True cyber defense should be ahead of the threats, not behind them.
To create faster, more effective cyber defense, Booz Allen is using NVIDIA’s RAPIDS platform to create an end-to-end graphics processing unit (GPU)-accelerated solution. It augments established cyber defenses with AI to proactively detect adversarial attacks at the edge or in the data center using real-time network data.
Bringing together Booz Allen’s cybersecurity and AI expertise and NVIDIA’s cutting-edge hardware and RAPIDS platform, this pioneering solution reads network data from sensor technologies, processes it, and uses AI to analyze the data in real-time, seamlessly integrating proactive systems with existing cyber defense and monitoring products and tools. This enables enterprises to keep up with advancing adversaries, reduce false positives in AI-only defense tools, and create greater efficiencies without completely overhauling defense systems.
This Booz Allen cyber AI solution supports cyber workflows, such as malware detection, domain-generated algorithm detection, credential misuse detection, and behavioral modeling.