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

BlackCat (ALPHV) Ransomware Levels Up for Stealth, Speed and Exfiltration

9 min read - This blog was made possible through contributions from Kat Metrick, Kevin Henson, Agnes Ramos-Beauchamp, Thanassis Diogos, Diego Matos Martins and Joseph Spero. BlackCat ransomware, which was among the top ransomware families observed by IBM Security X-Force in 2022, according to the 2023 X-Force Threat Intelligence Index, continues to wreak havoc across organizations globally this year. BlackCat (a.k.a. ALPHV) ransomware affiliates' more recent attacks include targeting organizations in the healthcare, government, education, manufacturing and hospitality sectors. Reportedly, several of these incidents resulted…

9 min read

Despite Tech Layoffs, Cybersecurity Positions are Hiring

4 min read - It’s easy to read today’s headlines and think that now isn’t the best time to look for a job in the tech industry. However, that’s not necessarily true. When you read deeper into the stories and numbers, cybersecurity positions are still very much in demand. Cybersecurity professionals are landing jobs every day, and IT professionals from other roles may be able to transfer their skills into cybersecurity relatively easily. As cybersecurity continues to remain a top business priority, organizations will…

4 min read

79% of Cyber Pros Make Decisions Without Threat Intelligence

4 min read - In a recent report, 79% of security pros say they make decisions without adversary insights “at least the majority of the time.” Why aren’t companies effectively leveraging threat intelligence? And does the C-Suite know this is going on? It’s not unusual for attackers to stay concealed within an organization’s computer systems for extended periods of time. And if their methods and behavioral patterns are unfamiliar, they can cause significant harm before the security team even realizes a breach has occurred.…

4 min read

Why People Skills Matter as Much as Industry Experience

4 min read - As the project manager at a large tech company, I always went to Jim when I needed help. While others on my team had more technical expertise, Jim was easy to work with. He explained technical concepts in a way anyone could understand and patiently answered my seemingly endless questions. We spent many hours collaborating and brainstorming ideas about product features as well as new processes for the team. But Jim was especially valuable when I needed help with other…

4 min read