Search papers, labs, and topics across Lattice.
This paper analyzes and improves the adversarial robustness of a CNN used for crystal-collimator alignment at CERN, focusing on time-series classification of beam-loss monitor data. They develop a preprocessing-aware wrapper that encodes time-series normalization, padding, and structured perturbations, enabling gradient-based robustness frameworks to operate on the deployed pipeline. Adversarial fine-tuning improves robust accuracy by up to 18.6% without sacrificing clean accuracy, and the study extends robustness analysis to sequence-level classification.
Adversarially fine-tuning a CNN for time-series classification in a high-stakes physics application (CERN collimator alignment) boosts robustness by nearly 20% without hurting clean accuracy.
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.
