arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.01352cs.LGastro-ph.HEastro-ph.IMhep-exphysics.data-an
收藏

MiniFool——深度神经网络中基于物理约束感知的最小化器对抗攻击

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

AI总结:

提出MiniFool算法,通过最小化结合χ²检验统计量与目标分数偏差的代价函数,生成物理感知的对抗样本,用于测试粒子与天体物理中的神经网络分类器,并量化网络决策的鲁棒性。

摘要:

在本文中,我们提出了一种新算法MiniFool,该算法实现了物理启发的对抗攻击,用于测试粒子物理和天体粒子物理中基于神经网络的分类任务。虽然我们最初为IceCube中微子天文台的天体物理tau中微子搜索开发了该算法,但我们将其应用于其他科学领域的更多数据,从而证明了其通用性。在此,我们将该算法应用于著名的MNIST数据集,以及大型强子对撞机CMS实验的开放数据。该算法基于最小化一个代价函数,该函数结合了基于χ²的检验统计量与期望目标分数的偏差。检验统计量根据实验不确定性量化了应用于数据的扰动的概率。对于我们研究的用例,我们发现翻转分类的可能性对于最初正确分类和错误分类的事件是不同的。当测试分类随攻击参数(该参数缩放实验不确定性)的变化时,可以量化网络决策的鲁棒性。此外,这允许测试未标记实验数据分类的鲁棒性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑