Researchers find a new way to train AI’s to protect them from deadly adversarial attacks
As more of the world comes to rely on AI adversarial attacks pose a particular challenge to companies and people in critical industries who are responsible for the safety of people and systems.
Key takeaways
- Today, most adversarial research focuses on image recognition systems, but deep learning based image reconstruction systems have also shown themselves to be vulnerable to adversarial attacks as well.
- The results still aren’t perfect though obviously and this is a work in progress but it’s a start.
- The work will be presented next week at the International Conference on Machine Learning.
Cite or link to this article
Griffin, M. (2020) 'Researchers find a new way to train AI’s to protect them from deadly adversarial attacks', 311 Institute, 14 July. Available at: https://www.311institute.com/adversarial-attacks-healthcare/ (Accessed: 1 October 2026).
Adversarial attacks, where hackers use the way that Artificial Intelligence (AI) sees the world against itself in order to trick into doing things it shouldn’t, are getting more widespread – whether it’s tricking Tesla’s into speeding into oncoming traffic or tricking hospital systems into giving patients the all clear when in fact they have terminal cancer.
Now, in response to this increasing threat, a team of researchers from University of Illinois (UI) have devise a new way to train AI’s in an attempt to try and protect them from these attacks, and as we rely on AI more and more in our daily lives it’s no exaggeration to say that their work could help save lives.
Today, most adversarial research focuses on image recognition systems, but deep learning based image reconstruction systems have also shown themselves to be vulnerable to adversarial attacks as well. This is particularly troubling in healthcare where the latter are often used to reconstruct medical images like CT or MRI scans from X-Ray data where a targeted adversarial attack could cause such a system to reconstruct a tumor in a scan where there isn’t one, or, as mentioned, vice versa giving doctors and patients false data which could be fatal.
As part of their research Bo Li and her colleagues at UI are have proposed a new method for training these deep learning systems so they’re more failproof and therefore trustworthy in what they call “safety critical scenarios.”
During their research they pitted the neural networks responsible for image reconstruction against other neural networks responsible for generating adversarial examples, in a style similar to GAN algorithms. Throughout iterative rounds the adversarial network attempts to fool the reconstruction network into producing things that aren’t part of the original data, or “ground truth.” The reconstruction network then continuously tweaks itself to avoid being fooled, which in turn makes it safer to use in the real world.
And as for the results when the researchers tested their adversarially trained neural network on two popular image data sets it was able to reconstruct the ground truth better than other neural networks that had been “fail proofed” with different methods.
The results still aren’t perfect though obviously and this is a work in progress but it’s a start. The work will be presented next week at the International Conference on Machine Learning.
FAQ
Why does this matter?
As more of the world comes to rely on AI adversarial attacks pose a particular challenge to companies and people in critical industries who are responsible for the safety of people and systems.
About the author
Matthew Griffin Founder, 311 Institute
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath."
Read full bio
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath." 15-time best selling author of the "Codex of the Future" series, Matthew is the Founder and Futurist in Chief of the 311 Institute, a global Futures and Deep Futures advisory firm working with royal households, world leaders, G7, G20, and G77 governments, NGOs, and multi-national mid and mega cap firms to help them explore, shape, and lead the next 50 years of business and society.
An award-winning YouTube creator with over a million followers, with an unrivalled global reach and impact, Matthew is a highly sought-after international keynote speaker, lecturer, and mentor who collaborates with global leaders through the United Nations Alliance of Civilizations (UNAOC) and United Nations General Assembly (UNGA) to shape pivotal initiatives such as the UN’s AI for Humanity program, the United Nations Conference of the Parties (UN COP), and the World Economic Forum in Davos.
As the former Global Head of Cloud, National Security, and Enterprise Sales for companies including Atos, Dell-EMC, and IBM, Matthew has a proven track record of building multi-billion dollar business units and turning failing divisions into market leaders. His ability to identify, analyse, and communicate the implications of hundreds of emerging technologies and trends is unparalleled, and his insights are trusted by many of the world’s most respected organisations, including ABB, Accenture, Adidas, AON, ARM, BCG, Centrica, Citi, Coca-Cola, Dentons, Deloitte, Dow Jones, EY, Google, KPMG, Lego, Legal & General, LinkedIn, Microsoft, PepsiCo, Qualcomm, RWE, Samsung, Siemens AG and Siemens Energy, T-Mobile, UBS, VISA, Walmart, Workday, Worldpay and many others.
Regularly featured in the global media including the AP, BBC, Bloomberg, CNBC, Discovery, Forbes, Khaleej Times, Telegraph, TIME, ViacomCBS, WIRED, and the WSJ, Matthews mission is to help organisations create a fair and sustainable future whose benefits are shared by everyone irrespective of their ability, background, or circumstances.
What future do you need to see?
Choose one to get started on security and privacy and the future of your organisation.
Sources and further reading
- reconstruct medical images ncbi.nlm.nih.gov
- Bo li technologyreview.com
- a new method arxiv.org
- Inside the world of ai that forges beautiful art and terrifying deepfakes technologyreview.com
- International Conference on Machine Learning icml.cc
Source: first published by the 311 Institute on 14 July 2020. Cite as: Griffin, M. (2020). Researchers find a new way to train AI’s to protect them from deadly adversarial attacks. 311 Institute. https://www.311institute.com/adversarial-attacks-healthcare/
You are welcome to quote this article with credit and a link to the original.