Researcher from the University of São Paulo Receives an International Award for a Tool that Prevents Hacker Attacks on Medical Systems
Erikson Aguiar, a PhD student from the Institute of Mathematics and Computational Sciences at the University of São Paulo in São Carlos, has made significant strides in enhancing the security of medical imaging systems against cyber threats. His innovative project,
presented at the “37th International Symposium on Computer-Based Medical Systems” in Guadalajara, Mexico, has garnered international recognition.
Addressing a Growing Threat in Medical Technology
The integration of artificial intelligence (AI) into medical diagnostics has brought about revolutionary improvements in disease detection and management. However, it has also introduced new vulnerabilities, as hackers increasingly target these systems. Malicious
attacks often involve subtle alterations to medical images, such as those from X-ray and MRI exams, aiming to deceive AI analysis and produce incorrect diagnoses. Such breaches not only jeopardize patient health but also undermine trust in technological advancements within healthcare.
Introducing Radar-Mix: A Beacon of Security
In response to these challenges, Erikson Júlio de Aguiar developed Radar-Mix, a pioneering tool designed to detect and analyze cyber attacks on AI-based medical image analysis systems. This breakthrough initiative was detailed in his article, “Radar-Mix: How to
Uncover Adversarial Attacks in Medical Image Analysis through Explainability,” which earned the Best Student Paper accolade at the CBMS 2024 conference held in June.
Erikson elucidates how Radar-Mix addresses these threats: “Artificial intelligence has been a great ally in diagnosing diseases, but at the same time, hackers have found ways to compromise these systems. Radar-Mix is a tool that makes it possible not only to detect
these attacks but also to understand how and where they happen, which is essential for ensuring the security of diagnoses.”
Advanced Visualization for Enhanced Security
The core strength of Radar-Mix lies in its use of advanced visualization tools such as Grad-CAM and Shap. These components provide a visual map, pinpointing which sections of an image have been manipulated during an attack. This feature not only aids in detection but
also offers an explanatory dimension by highlighting the exact nature and origin of the alterations. Consequently, Radar-Mix surpasses existing solutions by providing a comprehensive understanding of the attacks, thereby facilitating more robust protection strategies.
Recognition on an International Stage
The international acknowledgment at CBMS 2024 is a testament to the collaborative efforts between Erikson and his mentors, Professors Agma Traina and Caetano Traina from ICMC. Professor Agma remarked, “Seeing Erikson’s work be awarded at one of the world’s leading computer
and medical forums shows the quality of what we are developing here at ICMC.”
Impact and Implementation Potential
Radar-Mix’s modular design enables seamless integration into existing medical systems, offering hospitals and diagnostic centers an invaluable layer of defense against escalating cyber threats. The professor elaborated, “Radar-Mix was developed in a modular way, facilitating
its implementation and adaptation to different contexts. The interposition has been structured as a filter between access to services and servers, offering an additional layer of security and control.”
This tool is timely, as healthcare institutions globally, particularly in the United States, face increasing cyber threats. Erikson adds, “Radar-Mix helps to maintain trust in these AI systems, which is crucial for both doctors and patients.”
Open-Source Accessibility and Future Direction
One notable aspect of Radar-Mix is its availability as an open-source code, inviting further research and enhancements. This openness fosters collaboration and continuous improvement, essential elements in combating the ever-evolving landscape of cyber threats.
Looking ahead, Erikson is poised to advance his research. He is set to present a new dimension of Radar-Mix at the Spie Medical Imaging conference in February 2025 in California. Additionally, his collaboration with specialists at the University of Florida during his
one-year internship, supported by the São Paulo Research Foundation (Fapesp), will undoubtedly enrich his work.
A Pathway to a Promising Future
Professor Agma Traina underscores the valuable experience Erikson is gaining internationally, “Erikson is working with big names in the field of AI safety and this experience abroad will contribute a lot to his career, as he is an extremely dedicated student. I’m sure that
this award is just the start of a brilliant academic career.”
With such innovations as Radar-Mix, Erikson Aguiar is not only safeguarding future medical diagnostics but also paving the way for more secure and trustworthy applications of AI in healthcare. His contributions continue to illuminate the path toward a future where technology
and patient safety coexist harmoniously.
