Artificial intelligence (AI) in cybersecurity was a popular topic at RSA’s virtual conference this year, with good reason. Many tools rely on AI, using it for incident response, detecting spam and phishing and threat hunting. However, while AI security gets the session titles, digging deeper, it is clear that machine learning (ML) is really what makes it work. The reason is simple. ML allows for “high-value predictions that can guide better decisions and smart actions in real-time without humans stepping in.”

Yet, for all ML can do to improve intelligence and help AI security do more, ML has its flaws. ML, and by default AI, is only as smart as people teach it to be. If the AI isn’t learning the right algorithms, it could end up making your defenses weaker. Also, threat actors have the same access to AI and ML tools as defenders do. We are starting to see how attackers use ML to launch attacks, as well as how it can serve as an attack vector. Take a look at the benefits and dangers the experts discussed at RSA.

What Machine Learning Cybersecurity Gets Right

When provided the right data set, ML is good at seeing the big picture of the digital landscape you’re trying to defend. That’s according to Jess Garcia, technical lead with One eSecurity, who presented the RSA session ‘Me, My Adversary & AI: Investigating and Hunting with Machine Learning.’

Among the areas ML is most useful for security purposes are prediction, noise filtering and anomaly detection. “A malicious event tends to be an anomaly,” Garcia says. Defenders can use ML designed to detect anomalies for threat detection and threat hunting.

The size of the dataset matters when programming ML for AI security. As Younghoo Lee, Senior Data Scientist with Sophos, pointed out in the session ‘AI vs AI: Creating Novel Spam and Catching it with Text Generating AI,’ more training data gives better results and pre-trained language models matter for downstream tasks. Lee’s panel focused on spam creation and protections, but the advice applies across ML systems used for cybersecurity.

When Attackers Use ML or AI Security

In the session ‘Evasion, Poisoning, Extraction, and Inference: The Tools to Defend and Evaluate,’ presenters Beat Buesser, research staff member with IBM Research, and Abigail Goldsteen, research staff member with IBM, shared four different adversarial threats against ML. Attackers can use:

  • Evasion: Modify an input to influence a model
  • Poisoning: Add a backdoor to training data
  • Extraction: Steal a proprietary model
  • Inference: Learn about private data

“We’re seeing an increasing number of these real-world threats,” says Buesser. Threat actors use techniques that distort what the ML knows, some of which have life or death fallout for the AI security. One example is attackers who put stickers on a highway, forcing a self-driving vehicle to swerve into oncoming traffic. Another example shows how attackers can modify at-risk ML systems to allow them to bypass security filtering systems to let more phishing emails get through.

Balancing the Pros and Cons

ML systems designed to augment AI security have become a benefit to security teams. More automation means less burnout and more accurate threat detection and repair. However, because threat actors see ML as an attack vector, the team should also know where ML and AI exist within the company or agency beyond their systems. Once familiar with the ML and AI functions, they can learn where potential problems may linger and see how those can become springboards for an attack.

ML and AI security have the potential to change detection and prevention models for the better. You also still need the human touch to ensure ML isn’t causing security problems instead of solving them.

More from Intelligence & Analytics

The 13 Costliest Cyberattacks of 2022: Looking Back

2022 has shaped up to be a pricey year for victims of cyberattacks. Cyberattacks continue to target critical infrastructures such as health systems, small government agencies and educational institutions. Ransomware remains a popular attack method for large and small targets alike. While organizations may choose not to disclose the costs associated with a cyberattack, the loss of consumer trust will always be a risk after any significant attack. Let’s look at the 13 costliest cyberattacks of the past year and…

What Can We Learn From Recent Cyber History?

The Center for Strategic and International Studies compiled a list of significant cyber incidents dating back to 2003. Compiling attacks on government agencies, defense and high-tech companies or economic crimes with losses of more than a million dollars, this list reveals broader trends in cybersecurity for the past two decades. And, of course, there are the headline breaches and supply chain attacks to consider. Over recent years, what lessons can we learn from our recent history — and what projections…

When Logs Are Out, Enhanced Analytics Stay In

I was talking to an analyst firm the other day. They told me that a lot of organizations purchase a security information and event management (SIEM) solution and then “place it on the shelf.” “Why would they do that?” I asked. I spent the majority of my career in hardware — enterprise hardware, cloud hardware, and just recently made the jump to security software, hence my question. “Because SIEMs are hard to use. A SIEM purchase is just a checked…

4 Most Common Cyberattack Patterns from 2022

As 2022 comes to an end, cybersecurity teams globally are taking the opportunity to reflect on the past 12 months and draw whatever conclusions and insights they can about the threat landscape. It has been a challenging year for security teams. A major conflict in Europe, a persistently remote workforce and a series of large-scale cyberattacks have all but guaranteed that 2022 was far from uneventful. In this article, we’ll round up some of the most common cyberattack patterns we…