June 19, 2018 By Kacy Zurkus 3 min read

Humans versus machines: Who’s the better hacker? The advent of artificial intelligence (AI) brought with it a new set of attacks using adversarial AI, and this influx suggests the answer is likely machine.

With each innovation in technology comes the reality that attackers who study the security tools will find ways to exploit it. AI can make a phone number look like it’s coming from your home area code — and trick your firewall like a machine learning Trojan horse.

How can organizations fight an unknown enemy that’s not even human?

Humans vs. Machines: The Problem for Security

When cybersecurity company ZeroFOX asked if humans or machines were better hackers back in 2016, they took to Twitter with an automated E2E spear phishing attack. The results? According to their experiment, machines are much more effective at getting humans to click on malicious links.

AI models are built with a type of machine learning called deep neural networks (DNNs), which are similar to neurons in the human brain. DNNs make the machine capable of mimicking human behaviors like decision-making, reasoning and problem-solving.

When researchers and developers make an image, they are trying to picture an object, such as a cup, stop sign or cat. They can generate data that attempts to mimic real data by using machine learning — and each model brings that image closer to the real object. Now, imagine those pictures for medical imaging: The power of AI offers massive benefits when it comes to analyzing images.

So, what’s the problem for security? “Adversarial examples are (say, images) which have deliberately been modified to produce a desired response by a DNN,” according to IBM Research – Ireland.

The differences between the real and the fabricated are too small for the human eye to catch. Trained DNNs might catch those differences and classify the image as something all-together different — which is exactly what the attacker wants.

An Adversarial AI Arms Race

As the amount of data increases, nefarious actors will become more efficient at deploying new types of attacks by leveraging adversarial AI. This tactic will make attack attribution even more challenging.

“Adversaries will increase their use of machine learning to create attacks, experiment with combinations of machine learning and AI and expand their efforts to discover and disrupt the machine learning models used by defenders,” according to a 2018 cybercrime report. Enterprises must essentially prepare for an adversarial arms race.

Attacks will also become more affordable, according to the report — an additional bonus for attackers. An attacker can use an AI system to perform functions that would be virtually impossible for humans given the brain power and technical expertise required to achieve at scale.

Rage Against the Machine

What’s different about adversarial AI attacks? They can put on the same malicious offenses with great speed and depth. While AI is not a fully accessible tool for cybercriminals just yet, it’s weaponization is quickly growing more widespread. These threats can multiply the variations of the attack, vector or payload and increase the volume of the attacks. But outside of speed and scale, the attacks are fundamentally quite similar to current threat tactics.

So, how can organizations defend themselves? IBM recently released the Adversarial Robustness Toolbox to help defend DNNs against weaponized AI attacks, allowing researchers and developers to measure the robustness of their DNN models. This, in turn, will improve AI systems.

Sharing intelligence information with the cybersecurity community is also important in building strong defenses. The solution to adversarial AI will come from a combination of technology and policy, but all hands must be on deck. The risks threaten all sectors across public and private institutions. Coordinated efforts among key stakeholders will help to build a more secure future.

After all, the union of man and machine has the power to give defenders a leg up.

Visit the Adversarial Robustness Toolbox and contribute to IBM’s ongoing research into Adversarial AI Attacks

More from Artificial Intelligence

X-Force Threat Intelligence Index 2024 reveals stolen credentials as top risk, with AI attacks on the horizon

4 min read - Every year, IBM X-Force analysts assess the data collected across all our security disciplines to create the IBM X-Force Threat Intelligence Index, our annual report that plots changes in the cyber threat landscape to reveal trends and help clients proactively put security measures in place. Among the many noteworthy findings in the 2024 edition of the X-Force report, three major trends stand out that we’re advising security professionals and CISOs to observe: A sharp increase in abuse of valid accounts…

How I got started: Cyber AI/ML engineer

3 min read - As generative AI goes mainstream, it highlights the increasing demand for AI cybersecurity professionals like Maria Pospelova. Pospelova is currently a senior data scientist, and data science team lead at OpenText Cybersecurity. She also worked at Interest, an AI cybersecurity company acquired by MicroFocus and then by OpenText. She continues as part of that team today.Did you go to college? What did you go to school for?Pospelova: I graduated with a bachelor’s degree in computer science and a master’s degree…

Back to basics: Better security in the AI era

4 min read - The rise of artificial intelligence (AI), large language models (LLM) and IoT solutions has created a new security landscape. From generative AI tools that can be taught to create malicious code to the exploitation of connected devices as a way for attackers to move laterally across networks, enterprise IT teams find themselves constantly running to catch up. According to the Google Cloud Cybersecurity Forecast 2024 report, companies should anticipate a surge in attacks powered by generative AI tools and LLMs…

Topic updates

Get email updates and stay ahead of the latest threats to the security landscape, thought leadership and research.
Subscribe today