Deep neural networks (DNNs) are powerful tools for accurate predictions in various applications and have even shown to be superior to human experts in some domains, for instance for Melanoma detection.
However, they are vulnerable to data artifacts, such as band-aids, rulers or skin markers in the Melanoma detection task. In our previous blog post, we demonstrated the application of various model correction approaches to unlearn undesired model behavior and ultimately increase the security of these models.