# Uncovering Hidden Systematics in Neural Network Models for High Energy Physics

arXiv: https://arxiv.org/abs/2605.07470 · HTML: https://mlsanity.com/paper/2605.07470/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 14 of 14)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [A Living Review of Machine Learning for Particle Physics](https://mlsanity.com/paper/2102.02770/) (2021)
- [ParticleNet: Jet Tagging via Particle Clouds](https://mlsanity.com/paper/1902.08570/) (2019)
- [INFERNO: Inference-Aware Neural Optimisation](https://mlsanity.com/paper/1806.04743/) (2018)
- [End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data](https://mlsanity.com/paper/1902.08276/) (2019)
- [Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations](https://mlsanity.com/paper/2501.05588/) (2025)
- [End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data](https://mlsanity.com/paper/2104.14659/) (2021)
- [PCN: A Deep Learning Approach to Jet Tagging Utilizing Novel Graph Construction Methods and Chebyshev Graph Convolutions](https://mlsanity.com/paper/2309.08630/) (2023)
- [Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks](https://mlsanity.com/paper/2501.05656/) (2025)
- [MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks](https://mlsanity.com/paper/2511.01352/) (2025)
- [Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications](https://mlsanity.com/paper/2603.13970/) (2026)

## Abstract (arXiv)

Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flexibility enables unprecedented performance in high-energy physics (HEP) analyses, it also makes them sensitive to small variations in their inputs. Consequently, the propagation and estimation of systematic uncertainties in NN-based models remain an open challenge. There are indications that uncertainties derived in control regions or from nominal variations of input features can underestimate the true model uncertainty, potentially leaving biases unaccounted for. Inspired by insights from adversarial-attack studies in machine learning, we explore how subtle perturbations, fully consistent with the experimental uncertainties on the input observables, can lead to substantial changes in NN outputs, while keeping the one-dimensional and correlated input distributions nearly unchanged. Using a set of representative HEP tasks, including event classification and object identification, and testing across a variety of network architectures, we demonstrate that networks can be systematically "fooled" at significant rates within the allowed uncertainty envelopes. Building on this observation, we introduce a quantitative framework to probe and measure the hidden sensitivity of neural networks to realistic experimental variations, providing a practical path to evaluate and control their systematic uncertainty in physics analyses.