← Search

Awa Khouna

1 accepted papers

2025

From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks

NeurIPS 2025spotlight

The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counterfactual explanations, inadvertently increase the risk of model extraction attacks, enabling unauthorized replication of…

Cited by 0SourcecodeScholar