Adversarial Perturbations for Evolutionary Optimization

Unai Garciarena, Jon Vadillo, Alexander Mendiburu, Roberto Santana

Abstract: Sampling methods are a critical step for model-based evolutionary algorithms, their goal being the generation of new and promising individuals based on the information provided by the model. Adversarial perturbations have been proposed as a way to create samples that deceive neural networks. In this paper we introduce the idea of creating adversarial perturbations that correspond to promising solutions of the search space. A surrogate neural network is “fooled” by an adversarial perturbation algorithm until it produces solutions that are likely to be of higher fitness than the present ones. Using a benchmark of functions with varying levels of difficulty, we investigate the performance of a number of adversarial perturbation techniques as sampling methods. The paper also proposes a technique to enhance the effect that adversarial perturbations produce in the network. While adversarial perturbations on their own are not able to produce evolutionary algorithms that compete with state of the art methods, they provide a novel and promising way to combine local optimizers with evolutionary algorithms.