Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense
ISP RAS Research Center for Trusted Artificial Intelligence（俄罗斯科学院可信人工智能研究信息与处理中心）；Ivannikov Institute for System Programming of the Russian Academy of Sciences（俄罗斯科学院伊万诺夫系统编程研究所）；Moscow Institute of Physics and Technology (National Research University)（莫斯科物理技术学院（国家研究大学））；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；AIRI
Kirill Lukyanov, Mikhail Drobyshevskiy, Georgii Sazonov, Mikhail Soloviov, Ilya Makarov
随着可信AI（TAI）需求的增加，机器学习模型的可解释性和鲁棒性变得尤为重要。然而，许多现有工具忽视了图数据，并且很少将这两个方面结合起来。图神经网络（GNNs）已成为一种流行的方法，在各种任务中取得了最佳结果。我们介绍了GNN-AID（图神经网络分析、解释和防御），这是一个开源框架，旨在解决这一差距。GNN-AID是基于PyTorch-Geometric构建的Python库，支持先进的信任方法和架构层，允许用户使用攻击、防御和可解释性方法分析图数据集和GNN行为。GNN-AID还包含一个网页界面，提供图可视化工具和无代码功能，如交互式模型构建器，简化了GNN的探索和分析。该框架还支持MLOps技术，确保可重复性和结果版本控制，以高效地跟踪和重新访问分析结果。GNN-AID是一个灵活的工具，帮助开发人员创建、分析和定制图模型，同时提供预构建的数据集和模型以快速实验。研究人员可以使用该框架探索可解释性和鲁棒性之间的高级主题，测试防御策略，并结合方法以保护 against 不同类型的攻击。我们还展示了在图数据上应用防御措施时，防御对抗和污染攻击可能会产生冲突，突显了防御策略之间的复杂联系。
英文摘要：
The growing need for Trusted AI (TAI) highlights the importance of interpretability and robustness in machine learning models. However, many existing tools overlook graph data and rarely combine these two aspects into a single solution. Graph Neural Networks (GNNs) have become a popular approach, achieving top results across various tasks. We introduce GNN-AID (Graph Neural Network Analysis, Interpretation, and Defense), an open-source framework designed for graph data to address this gap. Built as a Python library, GNN-AID supports advanced trust methods and architectural layers, allowing users to analyze graph datasets and GNN behavior using attacks, defenses, and interpretability methods.
GNN-AID is built on PyTorch-Geometric, offering preloaded datasets, models, and support for any GNNs through customizable interfaces. It also includes a web interface with tools for graph visualization and no-code features like an interactive model builder, simplifying the exploration and analysis of GNNs. The framework also supports MLOps techniques, ensuring reproducibility and result versioning to track and revisit analyses efficiently.
GNN-AID is a flexible tool for developers and researchers. It helps developers create, analyze, and customize graph models, while also providing access to prebuilt datasets and models for quick experimentation. Researchers can use the framework to explore advanced topics on the relationship between interpretability and robustness, test defense strategies, and combine methods to protect against different types of attacks.
We also show how defenses against evasion and poisoning attacks can conflict when applied to graph data, highlighting the complex connections between defense strategies.
GNN-AID is available at \href{https://github.com/ispras/GNN-AID}{github.com/ispras/GNN-AID}
Mitigating the Structural Bias in Graph Adversarial Defenses
Department of Electrical Engineering, City University of Hong Kong（香港城市大学电子工程系）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Software Engineering, Sun Yat-sen University（中山大学软件工程学院）
AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
Xidian University（西安电子科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Chu Hai College（香港 Chu Hai 学院）；National University of Defense Technology（国防科技大学）；Shanghai JiaoTong University（上海交通大学）；Hubei University（湖北大学）
CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense
Department of Computer Science, Florida State University, Tallahassee, Florida, United States（佛罗里达州立大学计算机科学系）；Department of Mathematics, University of Wisconsin, Madison, Wisconsin, United States（威斯康星大学麦迪逊分校数学系）
Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
Faculty of Computer Science, University of Vienna（维也纳大学计算机学院）；Doctoral School Computer Science, University of Vienna（维也纳大学计算机博士学院）；Research Network Data Science University of Vienna（维也纳大学数据科学研究网络）
在这项工作中，我们提出了第一个后门攻击图神经网络（GNN）。具体来说，我们提出了一个\emph{subgraph based backdoor attack}的GNN图分类。在我们的后门攻击中，一旦预定义的子图被注入测试图，GNN分类器就预测攻击者为测试图选择的目标标签。我们在三个真实世界的图数据集上的实证结果表明，我们的后门攻击是有效的，对GNN的预测准确性的影响很小。此外，我们推广了一种基于随机平滑的认证防御来抵御我们的后门攻击。我们的实证结果表明，防御在某些情况下是有效的，但在其他情况下无效，突出了我们的后门攻击的新防御的需要。
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Northeastern University（东北大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Massachusetts Institute of Technology（麻省理工学院）；University of Minnesota（明尼苏达大学）
IoT-based Android Malware Detection Using Graph Neural Network With Adversarial Defense
Department of Computer and Information Sciences, Northumbria University（北安普顿大学计算机与信息科学系）；School of Computing, Engineering & Digital Technologies, Teesside University（泰赛大学计算、工程与数字技术学院）
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chengdu University of Information Technology（成都信息工程大学）；Chongqing Normal University（重庆师范大学）
SUSTech（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology of China（中国科学技术大学）
Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks
School of Cyber Science and Engineering, Sichuan University（四川大学网络空间安全学院）；School of Cyber Science and Engineering, Chengdu University of Information Technology（成都信息工程大学网络空间安全学院）；School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络空间安全学院）
Backdoor Attack on Vertical Federated Graph Neural Network Learning
Fudan University（复旦大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Zhejiang University（浙江大学）
TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support
Xidian University（西安电子科技大学）；Purdue University（普渡大学）；University of Alberta（阿尔伯塔大学）；Polish Academy of Sciences（波兰科学院）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）；Istinye University（伊斯蒂涅大学）
