Abstract
I will talk about innovation in the area of cyber security analytics - developing machine learning methods to detect and block cyber attacks (e.g. detecting ransomware within 4 seconds of execution and killing the underlying processes). Rather than just focusing on this as a 'black box', I'll pull it apart and talk about how we can use these methods to enable security practitioners to ask and answer questions about 'what' and 'why' these methods are flagging attacks (explainable AI). I'll also talk about resilience of machine learning methods to manipulation and adversarial attacks - how stable these approaches are to diversity and evolution of malware for example. Finally, I will reflect on this topic in the context of practical use.
Biography
Pete Burnap is Professor of Data Science & Cybersecurity at Cardiff University. He is Director of Cardiff’s NCSC/EPSRC Academic Centre of Excellence in Cyber Security Research (ACE-CSR). He leads AI for cybersecurity research at Airbus DTO on a part-time secondment basis. He has been involved in grants in worth in excess of £23m, leading large awards from EPSRC, ESRC and industry on cyber security analytics – the fusion of AI, Cybersecurity and Risk. He sits on the UK Government AI Council.