An empirical study of derivative-free-optimization algorithms for targeted black-box attacks in deep neural networks G Ughi, V Abrol, J Tanner Optimization and Engineering 23 (3), 1319-1346, 2022 | 19 | 2022 |
A Model-Based Derivative-Free Approach to Black-Box Adversarial Examples: BOBYQA G Ughi, V Abrol, J Tanner NeurIPS 2019 Workshop Beyond First Order Methods in ML, 2020 | 5 | 2020 |
Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery O O'Donoghue, P Duckworth, G Ughi, L Scheibenreif, K Khezeli, ... NeurIPS 2021 Workshop Machine Learning for Health, 2021 | 3 | 2021 |
Mutual Information of Neural Network Initialisations: Mean Field Approximations J Tanner, G Ughi International Seminar in Information Theory 2021, 2021 | 2 | 2021 |
Studies on neural networks: Information propagation at initialisation and robustness to adversarial examples G Ughi University of Oxford, 2022 | 1 | 2022 |
MUTUAL INFORMATION OF NEURAL NETWORK INITIALIZATIONS: A RANDOM MATRIX THEORY STUDY G Ughi, J Tanner | | 2023 |
Limits on simultaneous transmit and receive D Allwright, GA Antonucci, T Babb, A Evans, E Bowley, R Dakin, C Please, ... | | 2022 |
Federated causal inference for out-of-distribution generalization in predicting physiological effects of radiation exposure L Sanders, P Duckworth, O O'Donoghue, L Scheibenreif, G Ughi, ... AGU Fall Meeting Abstracts 2021, IN12A-04, 2021 | | 2021 |