X-Hacking: The Threat of Misguided AutoML

Sharma, Rahul; Mukherjee, Sumantrak; Sipka, Andrea; Hüllermeier, Eyke ; Vollmer, Sebastian Josef; Redyuk, Sergey und Selby, David Antony (2025): X-Hacking: The Threat of Misguided AutoML. Forty-second International Conference on Machine Learning (ICML 2025), Vancouver, Canada, 13. - 19. July 2025.

Abstract

Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified conclusions. This paper introduces the concept of X-hacking, a form of p-hacking applied to XAI metrics such as Shap values. We show how easily an automated machine learning pipeline can be adapted to exploit model multiplicity at scale: searching a set of ‘defensible’ models with similar predictive performance to find a desired explanation. We formulate the trade-off between explanation and accuracy as a multi-objective optimisation problem, and illustrate empirically on familiar real-world datasets that, on average, Bayesian optimisation accelerates X-hacking 3-fold for features susceptible to it, versus random sampling. We show the vulnerability of a dataset to X-hacking can be determined by information redundancy among features. Finally, we suggest possible methods for detection and prevention, and discuss ethical implications for the credibility and reproducibility of XAI.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• Sprache: Englisch