Persistent Classification: A New Approach to Stability of Data and Adversarial Examples
University of Arizona（亚利桑那大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；University of Texas San Antonio（德克萨斯大学圣安东尼奥分校）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）
Brian Bell, Michael Geyer, David Glickenstein, Keaton Hamm, Carlos Scheidegger, Amanda Fernandez, Juston Moore
There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifolds of interest, and that the structure of machine learning models may encourage classifiers to develop decision boundaries close to data points. This article proposes a new framework for studying adversarial examples that does not depend directly on the distance to the decision boundary. Similarly to the smoothed classifier literature, we define a (natural or adversarial) data point to be $(γ,σ)$-stable if the probability of the same classification is at least $γ$ for points sampled in a Gaussian neighborhood of the point with a given standard deviation $σ$. We focus on studying the differences between persistence metrics along interpolants of natural and adversarial points. We show that adversarial examples have significantly lower persistence than natural examples for large neural networks in the context of the MNIST and ImageNet datasets. We connect this lack of persistence with decision boundary geometry by measuring angles of interpolants with respect to decision boundaries. Finally, we connect this approach with robustness by developing a manifold alignment gradient metric and demonstrating the increase in robustness that can be achieved when training with the addition of this metric.
Zero-Sacrifice Persistent-Robustness Adversarial Defense for Pre-Trained Encoders
School of Cyber Science and Engineering, Sichuan University（四川大学网络科学与工程学院）；Key Laboratories of the Ministry of Education, Sichuan University（教育部重点实验室）；Tianfu Jiangxi Laboratory（天扶江西实验室）
The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
Microsoft Security Response Center（微软安全响应中心）；AIDOS Lab, University of Fribourg（弗里堡大学AIDOS实验室）；Department of Mathematics, Imperial College London（伦敦帝国理工学院数学系）；Queen Mary University of London（伦敦大学量子玛丽学院）；Imperial College London（伦敦帝国理工学院）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；The Alan Turing Institute（艾伦·图灵研究所）
Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning
Beijing University of Technology（北京工业大学）；The First Affiliated Hospital of Zhejiang University School of Medicine（浙江大学医学院附属第一医院）；Peking University First Hospital（北京大学第一医院）
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Georgia Institute of Technology（佐治亚理工学院）；University of Bristol（布里斯托大学）；University of Maryland（马里兰大学）；University College London（伦敦大学学院）；MATS；Astra；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Persistent Sheaf Laplacian Analysis of Protein Stability and Solubility Changes upon Mutation
Department of Mathematics, Michigan State University（数学系，密歇根州立大学）；The Frazer School（弗雷泽学校）；Lassiter High School（拉西特高中）；Department of Biochemistry and Molecular Biology, Michigan State University（生物化学与分子生物学系，密歇根州立大学）；Department of Electrical and Computer Engineering, Michigan State University（电气与计算机工程系，密歇根州立大学）
Can Adversarial Training Be Manipulated By Non-Robust Features?
Nanjing University（南京大学）；Chongqing University（重庆大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；Nanyang Technological University（南洋理工大学）；JD AI Research（京东人工智能研究院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
QSTAformer: A Quantum-Enhanced Transformer for Robust Short-Term Voltage Stability Assessment against Adversarial Attacks
School of Electrical Engineering, Northeast Electric Power University（东北电力大学电气工程学院）；State Grid Shandong Electric Power Company Jiaozhou Power Supply Company（山东电网济南供电分公司）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（香港科技大学土木与环境工程系）；State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of Electrical & Electronic Engineering, North China Electric Power University（可再生能源电力系统国家重点实验室，华北电力大学电气与电子工程学院）；Department of Electrical Engineering, City University of Hong Kong（香港城市大学电气工程系）
Do Wider Neural Networks Really Help Adversarial Robustness?
College of Computer Science, Zhejiang University（浙江大学计算机学院）；College of Information Science and Technology, Pennsylvania State University（宾夕法尼亚州立大学信息科学与技术学院）；Department of Computer Science, University of California, Los Angeles（加利福尼亚大学洛杉矶分校计算机科学系）
A stability theorem for bigraded persistence barcodes
Department of Mathematics, Rider University, Lawrenceville, NJ 08648, USA；Mathematical Institute of the Serbian Academy of Sciences；Department of Mathematics；Mechanics, Moscow State University, Russia；Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia；National Research University Higher School of Economics, Moscow, Russia；Department of Mathematics Education, Pusan National University, Busan, Republic of Korea；Statistics, University of Regina, Regina, Saskatchewan, Canada
