Adversarial Patch Generation for Automatic Program Repair

Automatic program repair (APR) has seen a growing interest in recent years with numerous techniques proposed. One notable line of research work in APR is search-based techniques which generate repair candidates via syntactic analyses and search for valid repairs in the generated search space. In this work, we explore an alternative approach which is inspired by the adversarial notion of bugs and repairs. Our approach leverages the deep learning Generative Adversarial Networks (GANs) architecture to suggest repairs that are as close as possible to human generated repairs. Preliminary evaluations demonstrate promising results of our approach (generating repairs exactly the same as human fixes for 21.2% of 500 bugs).