Abstract: The use of Machine Learning systems has drastically increased in the last few decades and the problems being solved become more and more complex. More specifically deep learning techniques allow one to reduce the human input and let the computer define the environment. However, it has been proved that this leads to vulnerable systems where a prediction can be corrupted by a malicious user. In the talk, Julie will discuss the impact of adversarial attacks and solutions to reduce the threats, in the cybersecurity context.
Bio: Julie Tiercelin is a recent Kent MSc graduate in Advanced Computer Science (Cloud Computing and Big Data). She has also an engineering degree with a speciality in Information Systems. During her studies, she has gained knowledge on cybersecurity and decided to mix it with Machine Learning to focus on the security of neural networks.
DetailsOpen to everyone, especially those interested in cyber security research,
Contact: Jason R.C. Nurse