Publications
3 results found
Bezou Vrakatseli E, Brueckner B, Thorburn L, 2023, SHAPE: A Framework for Evaluating the Ethicality of Influence, European Conference on Multi-Agent Systems
Agents often exert influence when interacting with humans and non-human agents. However, the ethical status of such influence is often unclear. In this paper, we present the SHAPE framework, which lists reasons why influence may be unethical. We draw on literature from descriptive and moral philosophy and connect it to machine learning to help guide ethical considerations when developing algorithms with potential influence. Lastly, we explore mechanisms for governing influential algorithmic systems, inspired by regulation in journalism, human subject research, and advertising.
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), Publisher: AAAI, Pages: 14946-14954, ISSN: 2374-3468
We introduce a novel method based on semidefinite program (SDP) for the tight and efficient verification of neural networks. The proposed SDP relaxation advances the present SoA in SDP-based neural network verification by adding a set of linear constraints based on eigenvectors. We extend this novel SDP relaxation by combining it with a branch-and-bound method that can provably close the relaxation gap up to zero. We show formally that the proposed approach leads to a provably tighter solution than the present SoA. We report experimental results showing that the proposed method outperforms baselines in terms of verified accuracy while retaining an acceptable computational overhead.
Schlagenhauf T, Yildirim F, Brueckner B, 2023, Siamese Basis Function Networks for Data-Efficient Defect Classification in Technical Domains, Berlin Workshop on Artificial Intelligence for Engineering Applications 2022
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.