Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning. (arXiv:2211.15926v1 [cs.CR])

Deep learning methods have gained increased attention in various applications
due to their outstanding performance. For exploring how this high performance
relates to the proper use of data artifacts and the accurate problem
formulation of a given task, interpretation models have become a crucial
component in developing deep learning-based systems. Interpretation models
enable the understanding of the inner workings of deep learning models and
offer a sense of security in detecting the misuse of artifacts in the input
data. Similar …

adversarial deep learning