English
Related papers

Related papers: ProvX: Generating Counterfactual-Driven Attack Exp…

200 papers

Graph Neural Networks (GNNs) have become a building block in graph data processing, with wide applications in critical domains. The growing needs to deploy GNNs in high-stakes applications necessitate explainability for users in the…

We present ProvG-Searcher, a novel approach for detecting known APT behaviors within system security logs. Our approach leverages provenance graphs, a comprehensive graph representation of event logs, to capture and depict data provenance…

Cryptography and Security · Computer Science 2023-12-20 Enes Altinisik , Fatih Deniz , Husrev Taha Sencar

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their…

Machine Learning · Computer Science 2025-03-13 Zhiwei Zhang , Minhua Lin , Junjie Xu , Zongyu Wu , Enyan Dai , Suhang Wang

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to…

Machine Learning · Computer Science 2024-10-29 Yinhan He , Wendy Zheng , Yaochen Zhu , Jing Ma , Saumitra Mishra , Natraj Raman , Ninghao Liu , Jundong Li

Modern cyber attackers use advanced zero-day exploits, highly targeted spear phishing, and other social engineering techniques to gain access and also use evasion techniques to maintain a prolonged presence within the victim network while…

Cryptography and Security · Computer Science 2023-10-03 Bibek Bhattarai , H. Howie Huang

With the development of information technology, the border of the cyberspace gets much broader, exposing more and more vulnerabilities to attackers. Traditional mitigation-based defence strategies are challenging to cope with the current…

Cryptography and Security · Computer Science 2020-12-15 Zhenyuan Li , Qi Alfred Chen , Runqing Yang , Yan Chen

Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we…

Machine Learning · Computer Science 2026-02-09 Yu Zhang , Sean Bin Yang , Arijit Khan , Cuneyt Gurcan Akcora

In this work, we propose the first backdoor attack to graph neural networks (GNN). Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification. In our backdoor attack, a GNN classifier predicts an…

Cryptography and Security · Computer Science 2021-12-20 Zaixi Zhang , Jinyuan Jia , Binghui Wang , Neil Zhenqiang Gong

Predictions made by graph neural networks (GNNs) usually lack interpretability due to their complex computational behavior and the abstract nature of graphs. In an attempt to tackle this, many GNN explanation methods have emerged. Their…

Machine Learning · Computer Science 2024-10-21 Zhong Li , Simon Geisler , Yuhang Wang , Stephan Günnemann , Matthijs van Leeuwen

Graph Neural Networks (GNNs) have significantly advanced various downstream graph-relevant tasks, encompassing recommender systems, molecular structure prediction, social media analysis, etc. Despite the boosts of GNN, recent research has…

Machine Learning · Computer Science 2025-01-08 Xiao Yang , Gaolei Li , Jianhua Li

Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explanation performance. We take the first step to study GNN…

Cryptography and Security · Computer Science 2024-06-06 Jiate Li , Meng Pang , Yun Dong , Jinyuan Jia , Binghui Wang

Graph neural networks (GNNs) have attracted considerable attention due to their diverse applications. However, the scarcity and quality limitations of graph data present challenges to their training process in practical settings. To…

Machine Learning · Computer Science 2024-11-07 Hanyang Yuan , Jiarong Xu , Renhong Huang , Mingli Song , Chunping Wang , Yang Yang

We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the…

Machine Learning · Computer Science 2021-06-02 Hao Yuan , Haiyang Yu , Jie Wang , Kang Li , Shuiwang Ji

Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph learning tasks. However, recent studies show that GNNs are vulnerable to both test-time evasion and training-time poisoning attacks that perturb the graph…

Cryptography and Security · Computer Science 2023-03-14 Binghui Wang , Meng Pang , Yun Dong

Deep graph learning models have demonstrated remarkable capabilities in processing graph-structured data and have been widely applied across various fields. However, their complex internal architectures and lack of transparency make it…

Machine Learning · Computer Science 2026-01-27 Jinlong Hu , Jiacheng Liu

Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as attacks. However, existing approaches rely on brittle, manually engineered rules to build…

Cryptography and Security · Computer Science 2026-03-19 Kushankur Ghosh , Mehar Klair , Kian Kyars , Euijin Choo , Jörg Sander

Graph Neural Networks (GNNs) are increasingly adopted across domains such as molecular biology and social network analysis, yet their black-box nature hinders interpretability and trust. This is especially problematic in high-stakes…

Machine Learning · Computer Science 2026-03-05 Matteo De Sanctis , Riccardo De Sanctis , Stefano Faralli , Paola Velardi , Bardh Prenkaj

Deep neural networks (DNNs) are increasingly being deployed in high-stakes applications, from self-driving cars to biometric authentication. However, their unpredictable and unreliable behaviors in real-world settings require new approaches…

Cryptography and Security · Computer Science 2025-10-01 Firas Ben Hmida , Abderrahmen Amich , Ata Kaboudi , Birhanu Eshete

Over the past decade, Graph Neural Networks (GNNs) have transformed graph representation learning. In the widely adopted message-passing GNN framework, nodes refine their representations by aggregating information from neighboring nodes…

Machine Learning · Computer Science 2025-11-26 Astrit Tola , Jack Myrick , Baris Coskunuzer

Graph neural network (GNN) with a powerful representation capability has been widely applied to various areas, such as biological gene prediction, social recommendation, etc. Recent works have exposed that GNN is vulnerable to the backdoor…

Machine Learning · Computer Science 2023-05-30 Haibin Zheng , Haiyang Xiong , Jinyin Chen , Haonan Ma , Guohan Huang