Google has announced a new AI Cyber Defense Initiative and proposed a new policy aimed at harnessing the power of artificial intelligence to bolster cybersecurity defenses globally.
This is designed to counteract evolving threats by leveraging AI’s capabilities to enhance threat detection, automate vulnerability management, and improve incident response efficiency.
The attackers need only one successful, novel threat to break through the best defenses. On the flip side, defenders need to deploy the best defenses at all times across increasingly complex digital terrain with no margin for error. Google calls this the “Defender’s Dilemma,” and there has never been a reliable way to tip that balance.
This is where AI enters the picture. Google believes AI at scale can tackle the Defender’s Dilemma. AI can do so by allowing security professionals and defenders to scale up their work in threat detection and related cybersecurity defense requirements.
The new initiative includes deploying AI-driven algorithms designed to identify and analyze patterns indicative of cyber threats. Using data generated across its global network, Google will train AI systems to learn from the full range of threats and teach them to adapt to new tactics employed by cybercriminals.
As part of the initiative, Google is also using AI to drive significant advances in vulnerability management. The idea is that by identifying vulnerabilities within software and systems, AI can significantly reduce the window of opportunity for attackers to exploit these weaknesses. Thrown into the mix is AI’s ability to suggest and implement fixes to vulnerabilities, streaming the patching process and, in doing so, further reducing the risk of a breach.
The initiative further outlines the use of AI in incident response and automates the analysis of indices to identify the source, method and extent of an attack.
Google is calling for a collaborative approach to recognizing the global nature of cyberthreats and calls for partnerships between industries and governments to share intelligence, best practices and advancements in AI-driven security measures.
Finally, Google announced today that it’s open-sourcing Magika, a new, AI-powered tool to aid defenders through file type identification, essential for detecting malware. Magika is already used to help protect products, including Gmail, drive, and safe browsing, and is used by Google’s VirusTotal team to foster a safer digital environment.
Google says Magika outperforms conventional file identification methods, providing an overall 30% accuracy boost and up to 95% higher precision on traditionally hard-to-identify but potentially problematic content such as VBA, JavaScript and Powershell.
