Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these complex models, but recent work has revealed their vulnerability to adversarial attacks where the explanation produced is appreciably different while the meaning and structure of the complex model's output remains similar. This prior work has focused on the existence of these weaknesses but not on their magnitude. Here we explore using an alternate search method with the goal of finding minimum viable perturbations, the fewest perturbations necessary to achieve a fixed similarity value between the original and altered text's explanation. Intuitively, a method that requires fewer perturbations to expose a given level of instability is inferior to one which requires more. This nuance allows for superior comparisons of the stability of explainability methods.
Analyzing the Impact of Adversarial Examples on Explainable Machine Learning
School of Computing and Information Science, Anglia Ruskin University, Cambridge, UK（计算与信息科学学院，安格利亚 Ruskin 大学）；Department of Computer Science and Engineering, Silicon University, Odisha, India（计算机科学与工程系，硅大学）；Department of Computer Science, University of the Pacific, Stockton, USA（计算机科学系，太平洋大学）
NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Embry-Riddle Aeronautical University（安柏瑞德航空大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Tennessee at Martin（田纳西大学马丁分校）；Bowling Green State University（博林格林州立大学）；Old Dominion University（奥多明尼昂大学）
Exploring Adversarial Attacks on Neural Networks: An Explainable Approach
Embry-Riddle Aeronautical University（安柏瑞德航空大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Tennessee at Martin（田纳西大学马丁分校）；Bowling Green State University（鲍灵格林州立大学）；Purdue University（普渡大学）；Trier University of Applied Sciences（特里尔应用技术大学）
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks
Department of Electrical and Computer Engineering, University of Illinois at Chicago（伊利诺伊大学芝加哥分校电气与计算机工程系）；Kitware Inc.（Kitware公司）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
ShrimpXNet: A Transfer Learning Framework for Shrimp Disease Classification with Augmented Regularization, Adversarial Training, and Explainable AI
East West University（东西大学）；Daffodil International University（达福迪尔国际大学）；North South University（北南大学）；University of Information Technology & Sciences（信息技术与科学大学）
Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4
The Center for Brains, Minds and Machines（大脑、心智与机器中心）；Massachusetts Institute of Technology（麻省理工学院）
现代在大脑评分竞赛中获得高分的视觉模型并不源于Vision Transformers。然而，在本文中，我们通过展示双流Transformer，CrossViT $~\textit{a la}$ Chen et al.（2021），在联合旋转不变和对抗优化程序下，在2022年总Brain-Score竞赛中获得第二名，提供了反对Vision Transformers（ViT）在感知上与人类视觉表示不一致的意外趋势的证据（Schrimpf et al.，2020 b）在所有视觉类别中平均，并且在比赛时在V4区域的最高可解释方差中排名第一。此外，我们目前的基于变换器的模型还实现了区域V4、IT和行为的更大的可解释方差，而不是生物启发的CNN（ResNet 50），其集成了类似于额叶V1的计算模块（Dapello等人，2020年）。为了评估优化方案对CrossViT架构的贡献，我们对不同优化的CrossViT的对抗鲁棒性，常见的腐败基准，中腹部刺激解释和特征反转进行了几次额外的实验。与我们最初的预期，我们的家庭的结果提供了临时支持$\textit{"All roads lead to Rome"}$参数通过联合优化规则，即使是非生物学动机的模型，如Vision Transformers的视觉。代码可在https://github.com/williamberrios/BrainScore-T…
ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment
Information Security Lab, University of Information Technology（信息安全部，信息科技大学）；Vietnam National University（越南国家大学）；School of Computer Science and Information Technology, Adelaide University（计算机科学与信息技术学院，阿德莱德大学）
Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
Beihang University（北京航空航天大学）；The University of Melbourne（墨尔本大学）；National Institute of Informatics（国立信息学研究所）；Shanghai Jiao Tong University（上海交通大学）；Chinese Academy of Sciences（中国科学院）
Adversarial Robustness May Be at Odds With Simplicity
Harvard University（哈佛大学）
机器学习中的当前技术到目前为止还不能学习对对抗性扰动鲁棒的分类器。然而，即使在存在随机扰动的情况下，它们也能够以非常高的精度学习非鲁棒分类器。为了解释这一差距，我们强调的假设，$\textit{robust classification may require more complex classifiers (i.e. more capacity) than standard classification.}$在这篇文章中，我们表明，这一假设确实是可能的，通过给出几个理论的分类任务和“简单”的分类器集的例子，其中：（1）存在一个简单的分类器具有高标准的准确性，并在随机$\ell_\infty$噪声下的高精度。(2)任何简单的分类器都不是鲁棒的：在$\ell_\infty$扰动的情况下，它必须具有高对抗损失。(3)鲁棒分类是可能的，但仅使用更复杂的分类器（在一些示例中，指数地更复杂）。此外，$\textit{there is a quantitative trade-off between robustness and standard accuracy among simple classifiers.}$这表明了对这种现象的另一种解释，这种现象出现在实践中：权衡可能不是因为分类任务固有地需要这样的权衡（如[Tsipras-Santurkar-Engstrom-Turner-Ma…
Enhancing Adversarial Robustness of IoT Intrusion Detection via SHAP-Based Attribution Fingerprinting
School of Information Technology, York University（约克大学信息科技学院）；School of Computer Science, University of Guelph（圭尔夫大学计算机科学学院）；National Research Council of Canada（加拿大国家研究委员会）
Domain-Adversarial Neural Network and Explainable AI for Reducing Tissue-of-Origin Signal in Pan-cancer Mortality Classification
Instituto Nacional de Medicina Genómica (INMEGEN)（国家基因组医学研究所）；Universidad Nacional Autónoma de México (UNAM)（墨西哥国立自治大学）；Centro de Ciencias de la Complejidad (C3)（复杂科学中心）
Distance Guided Generative Adversarial Network for Explainable Binary Classifications
Macao Polytechnic University（澳门理工大学）；Shanghai Jiao Tong University（上海交通大学）；East China Normal University（华东师范大学）；Zhejiang Sci-Tech University（浙江理工大学）；Hangzhou Normal University（杭州师范大学）
