{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T20:35:26Z","timestamp":1770323726108,"version":"3.49.0"},"reference-count":30,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    To address the challenge of anomaly detection in high-dimensional, heterogeneous accounting data, we propose multimodal fusion generative adversarial network (MF-GAN), a multimodal fusion framework that integrates synthesis and detection within a unified architecture. MF-GAN employs a dual-branch spatio-temporal generator: a temporal branch with regional residual learning to extract sequence dynamics, and a spatial branch based on convolutional networks to capture unstructured features from voucher images and associated text. A generative sample-augmentation mechanism\u2014combining bootstrap resampling with noise injection\u2014produces realistic anomalous samples, improving recall of rare anomaly types by 18.6% on a\n                    <jats:italic>corpus<\/jats:italic>\n                    of 180,000 real accounting records and the EnterpriseAccounting Anomaly Dataset (EAAD) dataset containing 3,200 labeled anomalies, thereby mitigating severe class imbalance. We further introduce a dynamic-weight joint optimization scheme that unifies generator and discriminator losses for collaborative training; ablating this component reduces performance by 21.4%, underscoring the importance of gradient co-training for generalization in unsupervised settings. Experimental results show that MF-GAN achieves 78.48% precision, 96.67% recall, and a 19% F1 improvement over mainstream baselines on EAAD. On the CBFAD dataset, MF-GAN attains 76.48% precision, 86.67% recall, and an 86.05% F1-score. The framework overcomes feature-extraction bottlenecks in high-dimensional time series and, through generative\u2013discriminative co-optimization, provides an interpretable and practical pathway for financial anti-fraud supervision\n                  <\/jats:p>","DOI":"10.7717\/peerj-cs.3550","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:20:22Z","timestamp":1770279622000},"page":"e3550","source":"Crossref","is-referenced-by-count":0,"title":["Anomaly synthesis and detection in accounting data\n                    <i>via<\/i>\n                    a generative adversarial network"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3623-9424","authenticated-orcid":true,"given":"Shan","family":"Zhang","sequence":"first","affiliation":[{"name":"Faculty of Economics and Management, The National University of Malaysia, Bangi, Selangor, Malaysia"},{"name":"Department of Accounting, School of Management, Wuhan Technology and Business University, Wuhan, Hubei, China"},{"name":"Research Center for Hubei Business Service and Development, Wuhan, Hubei, China"}]},{"given":"Lang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Financial Management, School of Accounting, Wuhan Qingchuan University, Wuhan, Hubei, China"}]},{"given":"Mi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Accounting, School of Management, Wuhan Technology and Business University, Wuhan, Hubei, China"},{"name":"Research Center for Hubei Business Service and Development, Wuhan, Hubei, China"}]},{"given":"Ziwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Accounting, School of Management, Wuhan Technology and Business University, Wuhan, Hubei, China"},{"name":"Research Center for Hubei Business Service and Development, Wuhan, Hubei, China"}]},{"given":"Wenqian","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Accounting, School of Management, Wuhan Technology and Business University, Wuhan, Hubei, China"},{"name":"Research Center for Hubei Business Service and Development, Wuhan, Hubei, China"}]}],"member":"4443","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"issue":"2","key":"10.7717\/peerj-cs.3550\/ref-1","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1007\/s11831-024-10174-8","article-title":"Generative adversarial networks (GANs) for medical image processing: recent advancements","volume":"32","author":"Ali","year":"2025","journal-title":"Archives of Computational Methods in Engineering"},{"key":"10.7717\/peerj-cs.3550\/ref-2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.04303","article-title":"Vision-LSTM: xLSTM as generic vision backbone","author":"Alkin","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-3","doi-asserted-by":"publisher","first-page":"104210","DOI":"10.1016\/j.jvcir.2024.104210","article-title":"Transferable adversarial attack on image tampering localization","volume":"102","author":"Cao","year":"2024","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.7717\/peerj-cs.3550\/ref-4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3773075","article-title":"Analytical survey of learning with low-resource data: from analysis to investigation","volume":"144","author":"Cao","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.7717\/peerj-cs.3550\/ref-5","doi-asserted-by":"publisher","first-page":"108256","DOI":"10.1016\/j.future.2025.108256","article-title":"Adaptively diagnosing system faults in microservice architecture: an autonomous predictive model construction framework","volume":"177","author":"Chen","year":"2025","journal-title":"Future Generation Computer Systems"},{"key":"10.7717\/peerj-cs.3550\/ref-6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.12258","article-title":"Lithium-ion battery capacity prediction via conditional recurrent generative adversarial network-based time-series regeneration","author":"Chowdhury","year":"2025"},{"issue":"3","key":"10.7717\/peerj-cs.3550\/ref-7","doi-asserted-by":"publisher","first-page":"101021","DOI":"10.1016\/j.suscom.2024.101021","article-title":"An intelligent security mechanism in mobile ad-hoc networks using precision probability genetic algorithms (PPGA) and deep learning technique (Stacked LSTM)","volume":"43","author":"Deivakani","year":"2024","journal-title":"Sustainable Computing: Informatics and Systems"},{"issue":"24","key":"10.7717\/peerj-cs.3550\/ref-8","doi-asserted-by":"publisher","first-page":"3935","DOI":"10.3390\/math12243935","article-title":"Exploring kernel machines and support vector machines: principles, techniques, and future directions","volume":"12","author":"Du","year":"2024","journal-title":"Mathematics"},{"key":"10.7717\/peerj-cs.3550\/ref-9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TDSC.2025.3620151","article-title":"A deep reinforcement learning approach to time delay differential game deception resource deployment","author":"He","year":"2025","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"issue":"6","key":"10.7717\/peerj-cs.3550\/ref-10","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1109\/TCYB.2025.3558941","article-title":"Correlation information enhanced graph anomaly detection via hypergraph transformation","volume":"55","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"4","key":"10.7717\/peerj-cs.3550\/ref-11","doi-asserted-by":"publisher","first-page":"127524","DOI":"10.1016\/j.neucom.2024.127524","article-title":"Recurrent context layered radial basis function neural network for the identification of nonlinear dynamical systems","volume":"580","author":"Kumar","year":"2024","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3550\/ref-12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.04758","article-title":"Anomaly detection with generative adversarial networks for multivariate time series","author":"Li","year":"2018"},{"key":"10.7717\/peerj-cs.3550\/ref-13","first-page":"8661","article-title":"SNED: superposition network architecture search for efficient video diffusion model","author":"Li","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3550\/ref-14","doi-asserted-by":"publisher","first-page":"100043","DOI":"10.1016\/j.eesus.2025.100043","article-title":"Machine learning prediction of hydrochar adsorption capacity for methylene blue with limited data: Inspired by generative adversarial network-based augmentation","volume":"1","author":"Liu","year":"2025","journal-title":"Energy & Environmental Sustainability"},{"key":"10.7717\/peerj-cs.3550\/ref-15","doi-asserted-by":"publisher","first-page":"110465","DOI":"10.1016\/j.ress.2024.110465","article-title":"Structural damage detection and localization via an unsupervised anomaly detection method","volume":"252","author":"Liu","year":"2024","journal-title":"Reliability Engineering & System Safety"},{"issue":"1","key":"10.7717\/peerj-cs.3550\/ref-16","doi-asserted-by":"publisher","first-page":"e0292140","DOI":"10.1371\/journal.pone.0292140","article-title":"An ensemble learning method with GAN-based sampling and consistency check for anomaly detection of imbalanced data streams with concept drift","volume":"19","author":"Liu","year":"2024","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj-cs.3550\/ref-17","first-page":"325","article-title":"Time-transformer: integrating local and global features for better time series generation","author":"Liu","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-18","doi-asserted-by":"publisher","first-page":"129431","DOI":"10.1016\/j.neucom.2025.129431","article-title":"Revisiting intelligent audit from a data science perspective","volume":"623","author":"Lu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3550\/ref-19","doi-asserted-by":"publisher","first-page":"13510","DOI":"10.1109\/ACCESS.2023.3240162","article-title":"Electric power audit text classification with multi-grained pre-trained language model","volume":"11","author":"Meng","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3550\/ref-20","doi-asserted-by":"publisher","first-page":"293","DOI":"10.18517\/ijaseit.15.1.20944","article-title":"Multivariate variable-based LSTM-AE model for solar power prediction","volume":"15","author":"Park","year":"2025","journal-title":"International Journal on Advanced Science, Engineering & Information Technology"},{"key":"10.7717\/peerj-cs.3550\/ref-21","first-page":"475","article-title":"Leveraging GANs to generate synthetic log files for smart troubleshooting in industry 4.0","author":"Partovian","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-22","doi-asserted-by":"publisher","first-page":"607","DOI":"10.2147\/ndt.s455279","article-title":"New therapeutic targets and drugs for schizophrenia beyond dopamine D2 receptor antagonists","volume":"20","author":"Peng","year":"2024","journal-title":"Neuropsychiatric Disease and Treatment"},{"issue":"6","key":"10.7717\/peerj-cs.3550\/ref-23","doi-asserted-by":"publisher","first-page":"4893","DOI":"10.1007\/s10462-022-10265-7","article-title":"Deep learning, graph-based text representation and classification: a survey, perspectives and challenges","volume":"56","author":"Pham","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"10.7717\/peerj-cs.3550\/ref-24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.09777","article-title":"Graph transformers: a survey","author":"Shehzad","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.18114","article-title":"EdgeRunner: auto-regressive auto-encoder for artistic mesh generation","author":"Tang","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-26","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/978-981-99-7882-3_5","article-title":"Distance-based classifiers","volume-title":"An Introduction to Image Classification: From Designed Models to End-to-End Learning","author":"Toennies","year":"2024"},{"key":"10.7717\/peerj-cs.3550\/ref-27","doi-asserted-by":"publisher","first-page":"142360\u2013142379","DOI":"10.1109\/ACCESS.2024.3466220","article-title":"Remote sensing image interpretation: deep belief networks for multi-object analysis","volume":"12","author":"Waqas Ahmed","year":"2024","journal-title":"IEEE Access"},{"issue":"10","key":"10.7717\/peerj-cs.3550\/ref-28","doi-asserted-by":"publisher","first-page":"6775","DOI":"10.1109\/TPAMI.2024.3387317","article-title":"Self-supervised learning for time series analysis: taxonomy, progress, and prospects","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.7717\/peerj-cs.3550\/ref-29","doi-asserted-by":"publisher","first-page":"6243","DOI":"10.1038\/s41598-024-56729-4","article-title":"A study on the influencing factors of corporate digital transformation: empirical evidence from Chinese listed companies","volume":"14","author":"Zhao","year":"2024","journal-title":"Scientific Reports"},{"issue":"4","key":"10.7717\/peerj-cs.3550\/ref-30","doi-asserted-by":"publisher","first-page":"112617","DOI":"10.1016\/j.knosys.2024.112617","article-title":"Supervised kernel principal component analysis-polynomial chaos-Kriging for high-dimensional surrogate modelling and optimization","volume":"305","author":"Zhao","year":"2024","journal-title":"Knowledge-Based Systems"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3550.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3550.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3550.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3550.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:20:27Z","timestamp":1770279627000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3550"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":30,"alternative-id":["10.7717\/peerj-cs.3550"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3550","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"article-number":"e3550"}}