Event Details

Dr. John Alasdair Warwicker - Assistant Professor (Lecturer) in Computer Science, Lancaster University Leipzig. Professor Warwicker has recently joined Leipzig in the Computer Science department. Please join the talk to find out about his research. Title: A Mixed-Integer Linear Programming Framework for the Adversarial Training of Neural Networks

Abstract: The training of neural networks (NNs) is a necessary task to improve their generalisation ability, measured by their performance on unseen inputs. However, even trained NNs can be vulnerable to adversarial inputs, which are minimally perturbed versions of standard inputs that are incorrectly labelled by the NN. The adversarial training of NNs can help to increase their robustness and guard against adversarial attacks. Recently, mixed-integer linear programming (MILP) models have been presented which are used to model the process of classification through trained NNs. One prominent application of such models is the ability to generate adversarial examples through providing constraints on the target input while minimising the level of perturbation. MILP models have also been presented for training NNs, showcasing comparable accuracy to traditional stochastic gradient descent approaches.

In this talk, we use recent advances in the field of MILP to present the adversarial training of NNs as an optimisation problem. We present a number of settings for the presented framework which allow for training against various settings of adversarially generated inputs, with the goal of increased robustness at minimal cost to performance. Experimental results on the MNIST data set of handwritten digits evaluate the performance of the proposed approach, and we discuss how the framework fits within the state-of-the-art.

After these results, we will briefly discuss other research streams in the theoretical analysis of hyper-heuristics and evolutionary algorithms.

https://www.lancasterleipzig.de/research/computing-communications/faculty/

Join this talk online