Distributed denial-of-service (DDoS) attacks have been around for over 20 years. Unfortunately, they will continue to haunt chief information security officers (CISOs), chief information officers (CIOs) — and pretty much anyone involved with IT for the foreseeable future.

These attacks are only growing in scope and size: While an attack comprised of only 150 requests per second would’ve been sufficient to zap many systems back in the day, DDoS attacks of 1,000 Gbps or greater are now common. And as Internet of Things (IoT) devices continue to proliferate, attacks will only intensify.

If the Mirai botnet taught us anything, it’s that the IoT magnifies the devastating blow of a DDoS attack. With the rise of artificial intelligence (AI), machine learning is already beginning to play an active role in detecting and stopping these attacks.

On the other hand, malicious actors can leverage this technology to mount attacks as well.

Launching DDoS Attacks Is Easy in the Age of AI

The complexities surrounding this topic are numerous. Rod Soto, director of security research at security software provider JASK, said launching a DDoS is (unfortunately) far too simple. Anybody can download a free tool capable of taking a company down.

“If you’re a small business and you have a generic website or shopping cart without additional protection, you are vulnerable,” Soto said.

While the simple-to-use tools can’t generate a massive volume of traffic, a knowledgeable malicious actor can leverage the IoT to create a botnet like Mirai. A large-scale campaign using an army of compromised IoT devices can easily scale up to 1 terabyte of data to engulf any system or service.

“Any kind of connected device that [a cybercriminal] can use to bounce or reflect off, they can command to attack a target that will add onto an existing attack,” Soto said.

Download the X-Force research report: Weaponizing the Internet of Things

Good vs. Evil: Who Wins the AI Battle?

To counteract these epic waves of traffic, Soto is counting on AI to play a critical role. In its most basic definition, he explained, machine learning is a way of teaching a computer to build an algorithm based on data. The algorithm learns what is normal and what is abnormal — and if it comes across something abnormal, it takes action.

“It’s a process that is best when working with data scientists, statistics and with as much data as possible,” Soto said. “You train it, it learns and extrapolates things that aren’t clear and can eventually make judgments on activity that you didn’t even train it to do.”

If the AI could talk (granted, some forms of AI actually do talk), it would say something like, “Hey, I know you didn’t train me to do this, but based on what I’m seeing, it appears that X, Y and Z — and I suggest you do A or B.”

On the dark side of the coin: Just as we can make machines think like humans, humans can learn as well. In many instances, malicious actors can figure out how to bypass the algorithm. This reality is where the problem lies for defenders of sensitive systems. According to Soto, once malicious actors figure out your algorithm, they can shift or skew the way the target defends itself and theoretically remove the barriers. When the DDoS comes in, the target goes down.

This point brings us back to the question of who wins out. If defenders and attackers can benefit equally from AI to serve their respective purposes, the one with the most resources will usually prevail.

“If your adversary has the resources, the money, the time, the machinery to process the data against a known target, then there’s a good chance they will be successful,” Soto said. “On the defending end, it’s basically the same story: You need the skill and resources. Until AI is commoditized, unfortunately, you will need the financial resources to use the technology.”

Addressing the Inevitable IoT Onslaught

Let’s face it: The type of AI that could be used to defend a DDoS attack is expensive, but hiring a third-party security company to assist in prevention efforts is money well spent. When engaging a third party, don’t wait until you are under attack before bringing in help. Like anything in the security world today, proactivity is critical.

Ultimately, not all the responsibility for preventing these large-scale attacks lies with the enterprise. The IoT industry must address the security issues inherent in connected devices before threat actors hijack them to attack vulnerable targets and cause significant damage. More robust defenses, such as distributor processing and machine learning, will be critical to deal with attacks of that magnitude.

“You can’t just manufacturer stuff that connects to the internet without any security consideration,” Soto said. “What’s scary is we buy these devices, we put it on at home or at work, and we forget about it.”

If there’s anything we have learned about DDoS, it’s that it’s profitable. As long as that’s the case, malicious actors will continue to wreak havoc. While malicious actors are always an enemy, make no mistake: Complacency can be an equally harmful adversary.

More from Artificial Intelligence

Machine Learning Applications in the Cybersecurity Space

3 min read - Machine learning is one of the hottest areas in data science. This subset of artificial intelligence allows a system to learn from data and make accurate predictions, identify anomalies or make recommendations using different techniques. Machine learning techniques extract information from vast amounts of data and transform it into valuable business knowledge. While most industries use these techniques, they are especially prominent in the finance, marketing, healthcare, retail and cybersecurity sectors. Machine learning can also address new cyber threats. There…

3 min read

Now Social Engineering Attackers Have AI. Do You? 

4 min read - Everybody in tech is talking about ChatGPT, the AI-based chatbot from Open AI that writes convincing prose and usable code. The trouble is malicious cyber attackers can use generative AI tools like ChatGPT to craft convincing prose and usable code just like everybody else. How does this powerful new category of tools affect the ability of criminals to launch cyberattacks, including social engineering attacks? When Every Social Engineering Attack Uses Perfect English ChatGPT is a public tool based on a…

4 min read

Can Large Language Models Boost Your Security Posture?

4 min read - The threat landscape is expanding, and regulatory requirements are multiplying. For the enterprise, the challenges just to keep up are only mounting. In addition, there’s the cybersecurity skills gap. According to the (ISC)2 2022 Cybersecurity Workforce Study, the global cybersecurity workforce gap has increased by 26.2%, which means 3.4 million more workers are needed to help protect data and prevent threats. Leveraging AI-based tools is unquestionably necessary for modern organizations. But how far can tools like ChatGPT take us with…

4 min read

Why Robot Vacuums Have Cameras (and What to Know About Them)

4 min read - Robot vacuum cleaner products are by far the largest category of consumer robots. They roll around on floors, hoovering up dust and dirt so we don’t have to, all while avoiding obstacles. The industry leader, iRobot, has been cleaning up the robot vacuum market for two decades. Over this time, the company has steadily gained fans and a sterling reputation, including around security and privacy. And then, something shocking happened. Someone posted on Facebook a picture of a woman sitting…

4 min read