Event logs are widely used to record the status of high-tech systems, making log anomaly detection important for monitoring those systems. We propose a graph-based method for unsupervised log anomaly detection, dubbed \textit{Logs2Graphs}, which first converts event logs into attributed, directed, and weighted graphs, and then leverages graph neural networks to perform graph-level anomaly detection. Specifically, we introduce OCDiGCN, a novel graph neural network model for detecting graph-level anomalies in a collection of attributed, directed, and weighted graphs. By coupling the graph representation and anomaly detection steps, OCDiGCN can learn a representation that is especially suited for anomaly detection, resulting in a high detection accuracy. For each detected anomaly, we provide a subset of nodes that are crucial in OCDiGCN’s predictions, offering useful insights for root cause diagnosis. Experiments on five benchmark datasets show that \textit{Logs2Graphs} matches or exceeds current top log anomaly detection methods on simple datasets and largely outperforms them on complex ones.
Wed 17 AprDisplayed time zone: Lisbon change
15:30 - 16:00 | |||
15:30 30mPoster | Graph Neural Networks based Log Anomaly Detection and Explanation Posters | ||
15:30 30mPoster | Unleashing the Giants: Enabling Advanced Testing for Infrastructure as Code Posters Daniel Sokolowski University of St. Gallen, David Spielmann University of St. Gallen, Guido Salvaneschi University of St. Gallen Link to publication DOI Pre-print | ||
15:30 30mPoster | Engineering Industry-Ready Anomaly Detection Algorithms Posters Ngoc-Thanh Nguyen Western Norway University of Applied Sciences, Rogardt Heldal , Patrizio Pelliccione Gran Sasso Science Institute, L'Aquila, Italy File Attached | ||
15:30 30mPoster | Behavior Trees with Dataflow: Coordinating Reactive Tasks in Lingua Franca Posters Alexander Schulz-Rosengarten Kiel University, Department of Computer Science, Akash Ahmad Kiel University, Department of Computer Science, Malte Clement Kiel University, Department of Computer Science, Reinhard von Hanxleden Kiel University, Benjamin Asch University of California, Berkeley, Marten Lohstroh University of California, Berkeley, Edward Lee University of California at Berkeley, Gustavo Quiros Siemens Technology, Ankit Shukla Siemens Technology | ||
15:30 30mPoster | A Study of Backporting Code in Open-Source Software for Characterizing Changesets Posters Debasish Chakroborti University of Saskatchewan, Chanchal K. Roy University of Saskatchewan, Canada, Kevin Schneider University of Saskatchewan | ||
15:30 30mPoster | Domain Knowledge is All You Need: A Field Deployment of LLM-Powered Test Case Generation in FinTech Domain Posters Zhiyi Xue East China Normal University, Liangguo East China Normal University, Senyue Tian East China Normal University, Xiaohong Chen ECNU, Pingping Li Guotai Junan Securities Co., Ltd, Liangyu Chen East China Normal University, Tingting Jiang Guotai Junan Securities Co., Ltd, Min Zhang East China Normal University | ||
15:30 30mPoster | A Transformer-based Model for Assisting Dockerfile Revising Posters Yiwen Wu National University of Defense Technology, Yang Zhang National University of Defense Technology, China, Tao Wang National University of Defense Technology, Huaimin Wang | ||
15:30 30mPoster | Poirot: Deep Learning for API Misuse Detection Posters Yi Li New Jersey Institute of Technology, Tien N. Nguyen University of Texas at Dallas, Shaohua Wang Central University of Finance and Economics, Aashish Yadavally University of Texas at Dallas | ||
15:30 30mPoster | Going Viral: Case Studies on the Impact of Protestware Posters Youmei Fan Nara Institute of Science and Technology, Dong Wang Kyushu University, Japan, Supatsara Wattanakriengkrai Nara Institute of Science and Technology, Hathaichanok Damrongsiri Nara Institute of Science and Technology, Christoph Treude Singapore Management University, Hideaki Hata Shinshu University, Raula Gaikovina Kula Nara Institute of Science and Technology | ||
15:30 30mPoster | Neural Exception Handling Recommender Posters Yi Li New Jersey Institute of Technology, Tien N. Nguyen University of Texas at Dallas, Yuchen Cai University of Texas at Dallas, Aashish Yadavally University of Texas at Dallas, Abhishek Mishra University of Texas at Dallas, Genesis Montejo University of Texas at Dallas | ||
15:30 30mPoster | Towards Leveraging Fine-Grained Dependencies to Check Requirements Traceability Correctness Posters Anamaria-Roberta Preda Johannes Kepler University Linz, Christoph Mayr-Dorn JOHANNES KEPLER UNIVERSITY LINZ, Atif Mashkoor Johannes Kepler University Linz, Wesley Assunção North Carolina State University, Alexander Egyed Johannes Kepler University Linz | ||
15:30 30mPoster | Imperfect Code Generation: Uncovering Weaknesses in Automatic Code Generation by Large Language Models Posters Xiaoli Lian Beihang University, China, Shuaisong Wang Beihang University, Jieping Ma Beihang University, Xin Tan Beihang University, Fang Liu Beihang University, Lin Shi Beihang University, Cuiyun Gao Harbin Institute of Technology, Li Zhang Beihang University | ||
15:30 30mPoster | Understanding the Strategies Used by Employees to Cope with Technostress in the Software Industry Posters Valtteri Siitonen University of Jyväskylä, Saima Ritonummi University of Jyväskylä, Markus Salo University of Jyväskylä, Henri Pirkkalainen Tampere University, Saija Mauno University of Jyväskylä | ||
15:30 30mPoster | Programmable and Semantic Connector for DNN Component Integration: a Software Engineering Perspective Posters | ||