Artificial intelligence is helping cybersecurity companies to create more advanced products with extended coverage. Because AI systems can “learn” to complete tasks, they are able to adapt on-the-fly to resist zero-day vulnerabilities.
In an interview last month, Microsoft Vice President of Enterprise & Cybersecurity Ann Johnson described AI as a “step change” in the field. The interview was published on the Microsoft News Center and recorded on the sidelines of the Interpol World 2017 Congress.
“When we see malware, we will be able to analyze it much more quickly by using artificial intelligence and machine learning,” Johnson said. “I think AI is the step change that we have all been waiting for.”
File photo: Moscow-based internet security giant Kaspersky has estimated that there are over 1,000 hackers in Russia specialising in financial crime
Kirill Kudryavtsev, AFP/File
READ NEXT: Cybersecurity is a $81.7 billion market – startups raking it in
AI’s not just being used for defensive purposes though. Johnson recognised that malicious use of the technology is inevitable, giving rise to a new breed of sophisticated threat. In the same way cybersecurity products will adapt to meet new threats, the threats themselves will adapt to resist the defences they meet.
“We have AI, but so do the bad guys,” Johnson said during the interview. “Malware [will become] adaptive in the wild, which I don’t think is that far off.”
Johnson discussed how cybersecurity companies will be able to fend off AI-powered attackers. She suggested it’d be best to approach the problem by studying existing defensive systems.
By looking at how AI is already being used, researchers could identify potential entry points for attacks before they’re used by hackers. Cybersecurity organisations should second guess malicious actors to anticipate potential problems.
A hacker in action.
Davide Restivo (CC BY-SA 2.0)
READ NEXT: Cyberattacks: What businesses can do
Johnson called on companies already using AI to share their threat intelligence data. This would facilitate the creation of a comprehensive “security graph” which could be analysed to identify weaknesses. She said it would be “impractical” for smaller firms to process their data themselves so a collaborative effort will be required to safeguard the future.
“Threat intelligence comes from companies, associations, industries and governments that have experienced cyberattacks,” Johnson said. “As you can imagine, that’s a lot of data, and it would be impractical for individual companies to take on the burden of collecting and analyzing it for their own use.”
Microsoft is already pursuing this technology with its Intelligent Security Graph. The graph comprises billions of data points created by millions of devices worldwide. When a threat is detected on the web, a Windows PC or a Microsoft cloud server, its presence is highlighted in the graph so affected customers can be automatically notified.
Microsoft campus
Microsoft
READ NEXT: Obama’s cybersecurity advisor: We need to tackle “statecraft”
The security graph is one of Microsoft’s main selling points for its Azure cloud service, indicating the value that customers now place on security. Microsoft alone can’t solve the cybersecurity issue though and neither is it trying to.
During the interview, Johnson presented cybersecurity as an incontrovertible reality of the modern world, “part of the fabric of society.” She said she now discusses “cyber-resilience” instead of “cybersecurity,” emphasising the change in meaning of the term.
By collaborating with outside organisations and proactively employing AI, Microsoft believes it can create a sustainable environment where threats are promptly responded to and breaches acknowledged. The approach won’t eradicate cybercrime entirely though.
“It is not going to stop. It is going to get worse. We will have to act faster, but we are not going to ‘stop’ it,” Johnson explained. “It’s like saying we are not going to have another murder or another bank robbery. Sadly, it is now part of the fabric of society.”
