How can we protect our IoT systems and data from outside attackers?
Today, many IoT systems in Sweden collect their data in clouds, which make them fragile and easy targets for outside attackers. Han Wang, researcher at RISE, will tell us about her work in using federated learning to decrease the sharing of data, and create more robust IoT-systems.
– One single small device can corrupt a whole network. When you use different AI-models, you need to know how your data is being trained and how your data is being used, says Han Wang.
Han Wang is currently working as a researcher at RISE Cybersecurity Unit. She received an Industrial Ph.D. degree in 2023 from Uppsala University with a thesis titled ”Robust and Efficient Federated Learning for IoT Security”. Today, she is working for RISE on several EU projects related to federated learning, cybersecurity, and adversarial AI.
– Traditionally, you send a large amount of data to a cloud and use the data to train a good model. With federated learning, you can keep your sensitive data in-house and still train your models, and make your IoT systems more robust and less vulnerable to cyberattacks, says Han Wang.
The seminar is free, digital and will be held in English.
