Dangerous malware is up 86%: Here's how AI can help

We’re excited to bring Transform 2022 back in person on July 19 and pretty much July 20-28. Join AI and data leaders for insightful conversations and exciting networking opportunities. Register today!

We’ve all heard that data breaches and other cybersecurity threats are on the rise, but the latest numbers, from the SiteLock 2022 Security Report, are truly staggering: “Highly serious malware” is up 86% year-over-year. Very serious threats are threats that can lead to stolen data, loss of customer trust, and damage to reputation and brand. And unfortunately, these threats often hit users when they do nothing but visit a website or click on a link.

More specifically, this includes downloading malware, phishing, redirects to malicious websites, and code injection. In other words, it is becoming easier for hackers to attack innocent users and destroy their lives and businesses.

As we all spend more time online in the post-COVID world, we run the risk of being more exposed to these types of threats. Cyber criminals are taking advantage of the telecommuting trend to attack remote workers and their company’s data. They are also using the pandemic as a cover to launch more phishing attacks as people are understandably distracted and preoccupied these days.

Big Data and AI can find malware

Big data and AI can help us fight back against these threats, as patterns emerge and new risks are identified. An IEEE study assessing AI-powered malware detection methods concludes that these techniques offer “significant benefits”, including in terms of accuracy, speed and scalability. For example, SafeDNS uses “continuous machine learning and user behavior analysis” to achieve 98% precision in detecting malware.

So how exactly does AI work in this context? Well, SafeDNS’s technology has built up a large “database of malware,” and data is the key to AI. The more data you have, the more accurately you can train your AI models. AI then continuously analyzes this data to look for new patterns of behavior that could indicate a threat.

This is just one example of how AI is being used to help us stay safe online. As the research makes clear, we need all the help we can get. With very serious malware on the rise, AI is a tool that can help us fight back.

What happens if malware is detected?

Detecting malware is of course not enough. If a machine learning model predicts that a website is hosting malware, what happens? In the case of platforms like SafeDNS, the user is warned and led away from the malicious site. This is done in real time so that the user never sees the dangerous content.

This approach is at the user level, but what about root cause? In other words, what happens to the website hosting the malware? According to SiteLock’s report, the answer is often “not enough” as the findings show that 92% of infected websites are not blacklisted by search engines.

One problem is, as CNN reports, if Google detects “permanent malware” on a site, it will block the website. However, many malicious sites are only active for a short period of time, so they may not be caught by Google’s algorithms. Plus, Google puts many of the sites it does detect into “quarantine” rather than “blacklist,” meaning they’re still accessible — just with a warning.

As a result, the damage can still be done and users can still be exposed to malware. This is a serious problem that needs to be addressed. Given the continuing prevalence of data breaches, it’s clear that more can be done to protect users – and AI is a tool that can help.

Attackers also use AI

There is a veritable arms race between cybercriminals and security experts, and AI plays a role on both sides. For example, a VentureBeat article explains that “AI-powered cyberthreats pose a significant risk to enterprises, especially those engaged in frequent communications that are prone to phishing.”

On the one hand, AI is being used by attackers to automate the process of launching phishing attacks and other malware. This means they can scale their operations and launch more attacks faster. On the other hand, AI is also used by security experts to automatically detect and block these attacks. As we have seen, AI-based malware detection is an effective way to protect users from exposure to dangerous content.

The side that doesn’t use AI effectively will lose the race. That’s why it’s so important for security experts to continue to develop and refine their AI-powered tools. Cyber criminals will not give up easily and we must be prepared to fight back.

AI is only becoming more important in the field of cybersecurity. As the SiteLock report makes clear, the need for AI-powered tools will only become more urgent as very serious malware becomes more prevalent. We need to be proactive in developing and deploying these tools if we want to stay ahead.

This is not a problem that will go away anytime soon, and we need to be prepared for the long haul. Cybersecurity is a critical issue and AI is one of the keys to keeping us safe.

Valerias Bangert is a strategy and innovation consultant, founder of three media outlets and published author.

DataDecision makers

Welcome to the VentureBeat Community!

DataDecisionMakers is where experts, including the technical people who do data work, can share data-related insights and innovation.

If you want to read about the latest ideas and up-to-date information, best practices and the future of data and data technology, join us at DataDecisionMakers.

You might even consider contributing an article yourself!