Privacy-preserving counterfactual explanations to help humans contest AI-based decisions

In the Cybersecurity field, very little work is done that measures how vulnerable is multi-objective counterfactual explanations to adversarial attacks and to what extent the privacy of the individuals can be preserved. Through this research, we aim to answer the question- (i) How easy it is to perform a membership inference attack through counterfactual explanations (ii) what is the defense mechanism to prevent a membership inference attack?