Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment

2026-04-07

AI Summary

This work addresses the vulnerability of temporal classification models to realistic adversarial perturbations in crystal collimator alignment tasks by proposing a preprocessing-aware robustness framework. By constructing a differentiable preprocessing wrapper that integrates temporal normalization, padding constraints, and structured perturbations into a CNN pipeline—combined with sliding-window modeling—the framework enables, for the first time, sequence-level adversarial robustness analysis. It is compatible with both Foolbox and Adversarial Robustness Toolbox (ART) attack methods and supports adversarial fine-tuning. Experiments demonstrate that adversarial fine-tuning improves robust accuracy by up to 18.6% without compromising clean-sample accuracy and reveals persistent adversarial misclassifications across adjacent temporal windows.

Abstract

In this paper, we analyze and improve the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at CERN's Large Hadron Collider (LHC) by classifying a beam-loss monitor (BLM) time series during crystal rotation. We formalize a local robustness property for this classifier under an adversarial threat model based on real-world plausibility. Building on established parameterized input-transformation patterns used for transformation- and semantic-perturbation robustness, we instantiate a preprocessing-aware wrapper for our deployed time-series pipeline: we encode time-series normalization, padding constraints, and structured perturbations as a lightweight differentiable wrapper in front of the CNN, so that existing gradient-based robustness frameworks can operate on the deployed pipeline. For formal verification, data-dependent preprocessing such as per-window z-normalization introduces nonlinear operators that require verifier-specific abstractions. We therefore focus on attack-based robustness estimates and pipeline-checked validity by benchmarking robustness with the frameworks Foolbox and ART. Adversarial fine-tuning of the resulting CNN improves robust accuracy by up to 18.6 % without degrading clean accuracy. Finally, we extend robustness on time-series data beyond single windows to sequence-level robustness for sliding-window classification, introduce adversarial sequences as counterexamples to a temporal robustness requirement over full scans, and observe attack-induced misclassifications that persist across adjacent windows.

Problem

• adversarial robustness
• time-series classification
• crystal collimator alignment
• beam-loss monitor
• sliding-window classification

Innovation

• adversarial robustness
• time-series classification
• preprocessing-aware wrapper
• sequence-level robustness
• adversarial fine-tuning