2024/07/17 by Clemens Otte, Otte, Clemens, Yinchong Yang +3
Computer Science · Neuroscience · #Neural Networks and Applications #Brain Tumor Detection and Classification #Advanced Neural Network Applications
paper · pdf · doi:10.48550/arxiv.2408.00783
The paper proposes a new testing approach for Deep Neural Networks (DNN) using gradient-free optimization to find perturbation chains that successfully falsify the tested DNN, going beyond existing grid-based or combinatorial testing. Applying it to an image segmentation task of detecting railway tracks in images, we demonstrate that the approach can successfully identify weaknesses of the tested DNN regarding particular combinations of common perturbations (e.g., rain, fog, blur, noise) on specific clusters of test images.