MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks

• URL: http://arxiv.org/abs/2511.01352v1
• Date: Mon, 03 Nov 2025 08:57:54 GMT
• Title: MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
• Authors: Lucie Flek, Oliver Janik, Philipp Alexander Jung, Akbar Karimi, Timo Saala, Alexander Schmidt, Matthias Schott, Philipp Soldin, Matthias Thiesmeyer, Christopher Wiebusch, Ulrich Willemsen,
• Abstract summary: MiniFool implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astroparticle physics.<n>The algorithm is based on minimizing a cost function that combines a $chi2$ based test-statistic with the deviation from the desired target score.
• Score: 37.35783762810649
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present a new algorithm, MiniFool, that implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astroparticle physics. While we initially developed the algorithm for the search for astrophysical tau neutrinos with the IceCube Neutrino Observatory, we apply it to further data from other science domains, thus demonstrating its general applicability. Here, we apply the algorithm to the well-known MNIST data set and furthermore, to Open Data data from the CMS experiment at the Large Hadron Collider. The algorithm is based on minimizing a cost function that combines a $\chi^2$ based test-statistic with the deviation from the desired target score. The test statistic quantifies the probability of the perturbations applied to the data based on the experimental uncertainties. For our studied use cases, we find that the likelihood of a flipped classification differs for both the initially correctly and incorrectly classified events. When testing changes of the classifications as a function of an attack parameter that scales the experimental uncertainties, the robustness of the network decision can be quantified. Furthermore, this allows testing the robustness of the classification of unlabeled experimental data.

Related papers

• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets [0.13265175299265505]
  We propose To-hull Uncertainty and Closure Ratio, which measures an uncertainty of trained model based on the convex hull of training data. It can observe the positional relation between the convex hull of the learned data and an unseen sample and infer how extrapolate the sample is from the convex hull.
  arXiv  Detail & Related papers  (2024-05-25T06:25:24Z)
• Goodness of fit by Neyman-Pearson testing [1.000352363234953]
  Neyman-Pearson strategy for hypothesis testing can be employed for goodness of fit if the alternative hypothesis is selected from data. New Physics Learning Machine (NPLM) methodology has been developed to target the detection of new physical effects in the context of high energy physics collider experiments. NPLM emerges as the more sensitive test to small departures of the data from the expected distribution and not biased towards detecting specific types of anomalies.
  arXiv  Detail & Related papers  (2023-05-23T15:01:45Z)
• Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification [60.60571130467197]
  In some machine learning applications the availability of labeled instances for supervised classification is limited while unlabeled instances are abundant. We introduce neuroevolutionary approaches that exploit unlabeled instances by using neuron coverage metrics computed on the neural network architecture encoded by each candidate solution.
  arXiv  Detail & Related papers  (2023-03-05T23:38:44Z)
• GFlowNets for AI-Driven Scientific Discovery [74.27219800878304]
  We present a new probabilistic machine learning framework called GFlowNets. GFlowNets can be applied in the modeling, hypotheses generation and experimental design stages of the experimental science loop. We argue that GFlowNets can become a valuable tool for AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2023-02-01T17:29:43Z)
• BSSAD: Towards A Novel Bayesian State-Space Approach for Anomaly Detection in Multivariate Time Series [0.0]
  We propose a novel and innovative approach to anomaly detection called Bayesian State-Space Anomaly Detection(BSSAD) The design of our approach combines the strength of Bayesian state-space algorithms in predicting the next state and the effectiveness of recurrent neural networks and autoencoders. In particular, we focus on using Bayesian state-space models of particle filters and ensemble Kalman filters.
  arXiv  Detail & Related papers  (2023-01-30T16:21:18Z)
• Deep Learning with Nonsmooth Objectives [0.0]
  We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior classification results in some special cases where the training data is either very small or unbalanced.
  arXiv  Detail & Related papers  (2021-07-14T02:01:53Z)
• The Causal Neural Connection: Expressiveness, Learnability, and Inference [125.57815987218756]
  An object called structural causal model (SCM) represents a collection of mechanisms and sources of random variation of the system under investigation. In this paper, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020) still holds for neural models. We introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences.
  arXiv  Detail & Related papers  (2021-07-02T01:55:18Z)
• Statistical model-based evaluation of neural networks [74.10854783437351]
  We develop an experimental setup for the evaluation of neural networks (NNs) The setup helps to benchmark a set of NNs vis-a-vis minimum-mean-square-error (MMSE) performance bounds. This allows us to test the effects of training data size, data dimension, data geometry, noise, and mismatch between training and testing conditions.
  arXiv  Detail & Related papers  (2020-11-18T00:33:24Z)
• Unsupervised Learning for Identifying Events in Active Target Experiments [1.4174475093445236]
  This article presents novel applications of unsupervised machine learning methods to the problem of event separation in an active target detector. The overarching goal is to group similar events in the early stages of the data analysis, thereby improving efficiency by limiting the computationally expensive processing of unnecessary events.
  arXiv  Detail & Related papers  (2020-08-06T16:49:39Z)
• Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection [66.05992706105224]
  In this paper, an effective anomaly detection framework is proposed utilizing Bayesian Optimization technique. The performance of the considered algorithms is evaluated using the ISCX 2012 dataset. Experimental results show the effectiveness of the proposed framework in term of accuracy rate, precision, low-false alarm rate, and recall.
  arXiv  Detail & Related papers  (2020-08-05T19:29:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.