MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
Bonn-Aachen International Center for Information Technology(波恩-亚琛国际信息科技中心);University of Bonn(波恩大学);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所);North Rhine-Westphalia(北莱茵-威斯特法伦州);RWTH Aachen University(亚琛工业大学);III. Physikalisches Institut B(物理研究所B);III. Physikalisches Institut A(物理研究所A);Physikalisches Institut(物理研究所);Erlangen Centre for Astroparticle Physics(埃朗根天体粒子物理中心);Friedrich-Alexander-Universität Erlangen-Nürnberg(埃朗根-纽伦堡弗里德里希-亚历山大大学);Dept. of Physics and Wisconsin IceCube Particle Astrophysics Center(物理系和威斯康星冰立方粒子天体物理学中心);University of Wisconsin—Madison(威斯康星大学麦迪逊分校)
Lucie Flek, Oliver Janik, Philipp Alexander Jung, Akbar Karimi, Timo Saala, Alexander Schmidt, Matthias Schott, Philipp Soldin, Matthias Thiesmeyer, Christopher… 展开作者
Lucie Flek, Oliver Janik, Philipp Alexander Jung, Akbar Karimi, Timo Saala, Alexander Schmidt, Matthias Schott, Philipp Soldin, Matthias Thiesmeyer, Christopher Wiebusch, Ulrich Willemsen
备注:
Submitted to Computing and Software for Big Science
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 $χ^2$ 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.
Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks
Institute of Mathematics(数学研究所);University of Würzburg(维尔茨堡大学);Technical University of Munich(慕尼黑工业大学);Institute of Computer Science(计算机科学研究所);CAIDAS;Institute of Mathematics, CAIDAS(CAIDAS数学研究所)
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
Michigan State University(密歇根州立大学);UC Santa Barbara(加州大学圣巴巴拉分校);University of Minnesota(明尼苏达大学);MIT-IBM Watson AI Lab, IBM Research(IBM研究院麻省理工-IBM沃森人工智能实验室)
Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization
University of Oxford(牛津大学);Southern University of Science and Technology(南方科技大学);University of Warwick(华威大学);European Centre for Medium-Range Weather Forecasts(欧洲中期天气预报中心)
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院(EPFL));Center for Data Science, New York University(纽约大学数据科学中心);École Normale Supérieure - PSL(巴黎高等师范学院-PSL大学);CNRS(法国国家科学研究中心);Courant Institute of Mathematical Sciences, New York University(纽约大学柯朗数学科学研究所);FAIR, META(元公司FAIR研究院)