Summary
I am a PhD candidate working on Neural Network Verification in the Safe AI Lab (SAIL) led by Prof. Alessio Lomuscio at Imperial College London's Department of Computing. I am also part of the Centre for Doctoral Training in Safe and Trusted AI.
Before joining Imperial, I completed a bachelor's and master's degree in Industrial Engineering and Management at Karlsruhe Institute of Technology. My bachelor's thesis was on Algorithms for Parallel Machine Scheduling, while my master's thesis was on Data-Efficient Image Classification Algorithms.
Publications
Conference
Bezou Vrakatseli E, Brueckner B, Thorburn L, 2023, SHAPE: A Framework for Evaluating the Ethicality of Influence, European Conference on Multi-Agent Systems
Lan J, Brueckner B, Lomuscio A, 2023, A Semidefinite Relaxation based Branch-and-Bound Method for Tight Neural Network Verification, AAAI Conference on Artificial Intelligence (AAAI23), AAAI, Pages:14946-14954, ISSN:2374-3468
Schlagenhauf T, Yildirim F, Brueckner B, Siamese Basis Function Networks for Data-Efficient Defect Classification in Technical Domains, Berlin Workshop on Artificial Intelligence for Engineering Applications 2022