Timezone: »

 
On the Connections between Counterfactual Explanations and Adversarial Examples
Martin Pawelczyk · Shalmali Joshi · Chirag Agarwal · Sohini Upadhyay · Hima Lakkaraju

Counterfactual explanations and adversarial examples have emerged as critical research areas for addressing the explainability and robustness goals of machine learning (ML). While counterfactual explanations were developed with the goal of providing recourse to individuals adversely impacted by algorithmic decisions, adversarial examples were designed to expose the vulnerabilities of ML models. In this work, we make one of the first attempts at formalizing the connections between counterfactual explanations and adversarial examples. More specifically, we theoretically analyze salient counterfactual explanation and adversarial example generation methods, and highlight the conditions under which they behave similarly. Our analysis demonstrates that several popular counterfactual explanation and adversarial example generation methods such as the ones proposed by Wachter et. al. and Carlini and Wagner (with mean squared error loss), and C-CHVAE and natural adversarial examples by Zhao et. al. are equivalent. We also bound the distance between counterfactual explanations and adversarial examples generated by Wachter et. al. and DeepFool methods for linear models.

Author Information

Martin Pawelczyk (University of Tuebingen)
Shalmali Joshi (Harvard University (SEAS))
Chirag Agarwal (Harvard University)
Sohini Upadhyay (Harvard University)
Hima Lakkaraju (Harvard)

More from the Same Authors