How Evolutionary Algorithms and Information Hiding deceive machines and humans for image recognition: A research program

Deep Neural Networks are used for a wide range of critical applications, notably for image recognition. The ability to deceive their recognition abilities is an active research domain, since successful deceptions may have disastrous consequences. Still, humans sometimes detect mistakes made by machines when they classify images. One can conceive a system able to solicit humans in case of doubts, namely when humans and machines may disagree. Using Information Hiding techniques, we describe a strategy to construct evolutionary algorithms able to fool both neural networks and humans for image recognition. Although this research is still exploratory, we already describe a concrete fitness function for a specific scenario. Additional scenarii and further research directions are provided.