Analyzing the Interpretability Robustness of Self-Explaining Models
This work highlights a critical vulnerability in interpretable AI for users relying on explanations, but it is incremental as it identifies a specific issue without proposing a solution.
The paper tackles the problem of interpretability robustness in self-explaining models (SEMs) by evaluating them against adversarial inputs, showing that explanations are not robust as they change significantly without altering model outputs.
Recently, interpretable models called self-explaining models (SEMs) have been proposed with the goal of providing interpretability robustness. We evaluate the interpretability robustness of SEMs and show that explanations provided by SEMs as currently proposed are not robust to adversarial inputs. Specifically, we successfully created adversarial inputs that do not change the model outputs but cause significant changes in the explanations. We find that even though current SEMs use stable co-efficients for mapping explanations to output labels, they do not consider the robustness of the first stage of the model that creates interpretable basis concepts from the input, leading to non-robust explanations. Our work makes a case for future work to start examining how to generate interpretable basis concepts in a robust way.