Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications
This addresses vulnerabilities in deep learning for particle physics, offering a method to find and mitigate adversarial effects, though it is incremental as it builds on existing adversarial attack concepts.
The authors tackled the problem of undetected deviations between simulation and data in high-energy physics machine learning applications by proposing CONSERVAttack, an adversarial attack that exploits remaining hypothetical deviations, which successfully fools models while evading standard validation checks.
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 need to constrain comparisons to specific regions, does not guarantee that all possible sources of deviations have been accounted for. We therefore propose a new adversarial attack - the CONSERVAttack - designed to exploit the remaining space of hypothetical deviations between simulation and data after the above mentioned tests. The resulting adversarial perturbations are consistent within the uncertainty bounds - evading standard validation checks - while successfully fooling the underlying model. We further propose strategies to mitigate such vulnerabilities and argue that robustness to adversarial effects must be considered when interpreting results from deep learning in particle physics.