A Little Fog for a Large Turn
This work addresses the need for more natural and general adversarial testing methods in autonomous navigation, though it is incremental as it builds on existing generative adversarial network techniques.
The paper tackled the problem of adversarial perturbations in neural networks by introducing a method to generate natural-looking adversarial weather conditions, such as fog, for testing autonomous navigation models, showing these images serve as an effective testbed.
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. To this end, we introduce a general notion of adversarial perturbations, which can be created using generative models and provide a methodology inspired by Cycle-Consistent Generative Adversarial Networks to generate adversarial weather conditions for a given image. Our formulation and results show that these images provide a suitable testbed for steering models used in Autonomous navigation models. Our work also presents a more natural and general definition of Adversarial perturbations based on Perceptual Similarity.