[2603.13970] Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications

Computer Science > Machine Learning arXiv:2603.13970 (cs) [Submitted on 14 Mar 2026 (v1), last revised 8 Apr 2026 (this version, v2)] Title:Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications Authors:Philip Bechtle, Lucie Flek, Philipp Alexander Jung, Akbar Karimi, Timo Saala, Alexander Schmidt, Matthias Schott, Philipp Soldin, Christopher Wiebusch, Ulrich Willemsen View a PDF of the paper titled Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications, by Philip Bechtle and 9 other authors View PDF HTML (experimental) Abstract:In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our understanding of fundamental phenomena. Increasingly, deep learning models are applied to analyze both simulated and experimental data. In most experiments, a rigorous regime of testing for physically motivated systematic uncertainties is in place. The numerical evaluation of these tests for differences between the data on the one side and simulations on the other side quantifies the effect of potential sources of mismodelling on the machine learning output. In addition, thorough comparisons of marginal distributions and (linear) feature correlations between data and simulation in "control regions" are applied. However, the guidance by physical motivation, and the ne...