{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/one-class-adversarial-nets-for-fraud","title":"One-Class Adversarial Nets for Fraud Detection","arxiv_id":"1803.01798","date":"2018-03-05","proceeding":null,"authors":["Panpan Zheng","Shuhan Yuan","Xintao Wu","Jun Li","Aidong Lu"],"abstract":"Many online applications, such as online social networks or knowledge bases,\nare often attacked by malicious users who commit different types of actions\nsuch as vandalism on Wikipedia or fraudulent reviews on eBay. Currently, most\nof the fraud detection approaches require a training dataset that contains\nrecords of both benign and malicious users. However, in practice, there are\noften no or very few records of malicious users. In this paper, we develop\none-class adversarial nets (OCAN) for fraud detection using training data with\nonly benign users. OCAN first uses LSTM-Autoencoder to learn the\nrepresentations of benign users from their sequences of online activities. It\nthen detects malicious users by training a discriminator with a complementary\nGAN model that is different from the regular GAN model. Experimental results\nshow that our OCAN outperforms the state-of-the-art one-class classification\nmodels and achieves comparable performance with the latest multi-source LSTM\nmodel that requires both benign and malicious users in the training phase.","url_abs":"http://arxiv.org/abs/1803.01798v2","url_pdf":"http://arxiv.org/pdf/1803.01798v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"one-class-adversarial-nets-for-fraud","repo_url":"https://github.com/PanpanZheng/OCAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fraud-detection","task_name":"Fraud Detection"},{"task_slug":"one-class-classification","task_name":"One-Class Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.01798","atlas_url":"https://app.syntology.ai/?focus=1803.01798","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}