English
Related papers

Related papers: Dual Explanations via Subgraph Matching for Malwar…

200 papers

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures.…

Machine Learning · Computer Science 2026-03-03 Yue Niu , Zhaokai Sun , Jiayi Yang , Xiaofeng Cao , Rui Fan , Xin Sun , Hanli Wang , Wei Ye

Explainable Graph Neural Networks (GNNs) have been developed and applied to drug-protein binding prediction to identify the key chemical structures in a drug that have active interactions with the target proteins. However, the key…

Biomolecules · Quantitative Biology 2023-09-25 Yang Wang , Zanyu Shi , Timothy Richardson , Kun Huang , Pathum Weerawarna , Yijie Wang

Malware is being increasingly threatening and malware detectors based on traditional signature-based analysis are no longer suitable for current malware detection. Recently, the models based on machine learning (ML) are developed for…

Cryptography and Security · Computer Science 2021-01-18 Yuzhou Lin , Xiaolin Chang

Explainability is crucial for the application of black-box Graph Neural Networks (GNNs) in critical fields such as healthcare, finance, cybersecurity, and more. Various feature attribution methods, especially the perturbation-based methods,…

Machine Learning · Computer Science 2024-12-31 Xingping Xian , Jianlu Liu , Chao Wang , Tao Wu , Shaojie Qiao , Xiaochuan Tang , Qun Liu

AI methods have been proven to yield impressive performance on Android malware detection. However, most AI-based methods make predictions of suspicious samples in a black-box manner without transparency on models' inference. The expectation…

Cryptography and Security · Computer Science 2022-11-21 Zhi Lu , Vrizlynn L. L. Thing

Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malware detection, graph representations (e.g., function call…

Cryptography and Security · Computer Science 2024-10-01 Jingnan Zheng , Jiaohao Liu , An Zhang , Jun Zeng , Ziqi Yang , Zhenkai Liang , Tat-Seng Chua

Detecting packed executables is a critical step in malware analysis, as packing obscures the original code and complicates static inspection. This study evaluates both classical feature-based methods and deep learning approaches that…

Cryptography and Security · Computer Science 2025-12-18 Ehab Alkhateeb , Ali Ghorbani , Arash Habibi Lashkari

In recent years, pre-training Graph Neural Networks (GNNs) through self-supervised learning on unlabeled graph data has emerged as a widely adopted paradigm in graph learning. Although the paradigm is effective for pre-training powerful GNN…

Machine Learning · Computer Science 2025-10-28 Yuhan Yang , Xingbo Fu , Jundong Li

Graph super-resolution, the task of inferring high-resolution (HR) graphs from low-resolution (LR) counterparts, is an underexplored yet crucial research direction that circumvents the need for costly data acquisition. This makes it…

Machine Learning · Computer Science 2025-11-13 Pragya Singh , Islem Rekik

Graph Neural Networks (GNNs) are widely used in many modern applications, necessitating explanations for their decisions. However, the complexity of GNNs makes it difficult to explain predictions. Even though several methods have been…

Machine Learning · Computer Science 2022-11-04 Tien-Cuong Bui , Van-Duc Le , Wen-Syan Li , Sang Kyun Cha

With the rapid growth of Android malware, many machine learning-based malware analysis approaches are proposed to mitigate the severe phenomenon. However, such classifiers are opaque, non-intuitive, and difficult for analysts to understand…

Cryptography and Security · Computer Science 2020-08-14 Ming Fan , Wenying Wei , Xiaofei Xie , Yang Liu , Xiaohong Guan , Ting Liu

Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial…

Cryptography and Security · Computer Science 2026-04-07 Andrew Wheeler , Kshitiz Aryal , Maanak Gupta

Provenance graph-based intrusion detection systems are deployed on hosts to defend against increasingly severe Advanced Persistent Threat. Using Graph Neural Networks to detect these threats has become a research focus and has demonstrated…

Cryptography and Security · Computer Science 2025-08-11 Weiheng Wu , Wei Qiao , Teng Li , Yebo Feng , Zhuo Ma , Jianfeng Ma , Yang Liu

Most behavioral detectors of malware remain specific to a given language and platform, mostly PE executables for Windows. The objective of this paper is to define a generic approach for behavioral detection based on two layers respectively…

Cryptography and Security · Computer Science 2009-02-03 Gregoire Jacob , Herve Debar , Eric Filiol

Interpretable Graph Neural Networks (GNNs) aim to reveal the underlying reasoning behind model predictions, attributing their decisions to specific subgraphs that are informative. However, existing subgraph-based interpretable methods…

Machine Learning · Computer Science 2025-05-02 Jie Yang , Yuwen Wang , Kaixuan Chen , Tongya Zheng , Yihe Zhou , Zhenbang Xiao , Ji Cao , Mingli Song , Shunyu Liu

The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning. The objective of GNN explainability is to…

Machine Learning · Computer Science 2023-10-31 Jialin Chen , Shirley Wu , Abhijit Gupta , Rex Ying

Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN), emerged as powerful tools for unraveling how different…

Machine Learning · Computer Science 2026-05-22 Ping Xiong , Thomas Schnake , Grégoire Montavon , Klaus-Robert Müller , Shinichi Nakajima

The task of graph-level anomaly detection (GLAD) is to identify anomalous graphs that deviate significantly from the majority of graphs in a dataset. While deep GLAD methods have shown promising performance, their black-box nature limits…

Machine Learning · Computer Science 2026-02-12 Qiuran Zhao , Kai Ming Ting , Xinpeng Li

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node…

Machine Learning · Computer Science 2020-11-16 Dongsheng Luo , Wei Cheng , Dongkuan Xu , Wenchao Yu , Bo Zong , Haifeng Chen , Xiang Zhang

Comprehensible neural network explanations are foundations for a better understanding of decisions, especially when the input data are infused with malicious perturbations. Existing solutions generally mitigate the impact of perturbations…

Machine Learning · Computer Science 2025-02-21 Yicong Li , Kuanjiu Zhou , Shuo Yu , Qiang Zhang , Renqiang Luo , Xiaodong Li , Feng Xia