{"type":"ScholarlyArticle","title":"Preventing Attacks in Interbank Credit Rating with Selective-aware Graph Neural Network","authors":[{"name":"Junyi Liu","slug":"junyi-liu","given":"Junyi","family":"Liu","affiliation":"Department of Computer Science and Technology , Tongji University , Shanghai , China; Shanghai Artificial Intelligence Laboratory , Shanghai , China"},{"name":"Dawei Cheng","slug":"dawei-cheng","given":"Dawei","family":"Cheng","affiliation":"Department of Computer Science and Technology , Tongji University , Shanghai , China; Key Laboratory of Artificial Intelligence , Ministry of Education , Shanghai , China; Shanghai Artificial Intelligence Laboratory , Shanghai , China"},{"name":"Changjun Jiang","slug":"changjun-jiang","given":"Changjun","family":"Jiang","affiliation":"Department of Computer Science and Technology , Tongji University , Shanghai , China; Shanghai Artificial Intelligence Laboratory , Shanghai , China"}],"abstract":"Accurately credit rating on Interbank assets is essential for a healthy financial environment and substantial economic development. But individual participants tend to provide manipulated information in order to attack the rating model to produce a higher score, which may conduct serious adverse effects on the economic system, such as the 2008 global financial crisis. To this end, in this paper, we propose a novel selective-aware graph neural network model (SA-GNN) for defense the Interbank credit rating attacks. In particular, we first simulate the rating information manipulating process by structural and feature poisoning attacks. Then we build a selective-aware defense graph neural model to adaptively prioritize the poisoning training data with Bernoulli distribution similarities. Finally, we optimize the model with weighed penalization on the objection function so that the model could differentiate the attackers. Extensive experiments on our collected real-world Interbank dataset, with over 20 thousand banks and their relations, demonstrate the superior performance of our proposed method in preventing credit rating attacks compared with the state-of-the-art baselines.","doi":"10.24963/ijcai.2023/675","url":"https://ijcai.org/proceedings/2023/675","pdf":"https://ijcai.org/proceedings/2023/0675.pdf","markdown":"https://ijcai.org/proceedings/2023/675.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/675","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"AI for Good","track":"AI for Good","number":675,"pages":{"first":6085,"last":6093},"keywords":["AI for Good: Multidisciplinary Topics and Applications","AI for Good: Data Mining"],"videos":[],"references":[{"position":1,"raw":"Year Method 0% 5% 10% 15% 20% 25% GCN 49.62 46.34 44.60 44.18 43.67 43.59 GAT 50.89 48.89 45.22 45.64 43.83 44.72 2016 RGCN 55.55 53.29 49.59 47.17 45.53 44.48 Pro-GNN 54.88 49.98 49.90 48.29 46.03 45.65 SA-GNN 56.07 55.88 54.53 53.89 52.16 51.93 GCN 51.06 50.39 48.68 48.92 48.34 47.98 GAT 51.89 50.15 49.59 49.38 49.55 49.29 2017 RGCN 52.17 51.57 49.62 49.24 48.20 47.61 Pro-GNN 52.11 50.16 50.87 45.63 46.37 47.94 SA-GNN 52.73 52.65 52.58 52.48 52.40 51.05 GCN 47.16 45.24 45.08 45.22 44.79 43.61 GAT 48.20 47.62 47.46 45.44 45.85 44.41 2018 RGCN 48.29 47.99 47.33 45.81 45.94 45.09 Pro-GNN 48.85 48.05 47.78 45.91 45.57 45.20 SA-GNN 49.59 49.47 48.94 47.78 47.24 46.23 GCN 55.21 53.07 51.67 50.85 49.89 49.98 GAT 57.60 54.32 53.64 52.38 51.49 50.67 2019 RGCN 56.02 54.18 52.86 50.82 50.08 50.28 Pro-GNN 53.83 49.45 47.74 46.59 49.11 48.65 SA-GNN 62.41 62.37 62.34 60.16 60.07 58.76","title":"Year Method","authors":null,"year":null,"venue":"Year Method","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Agarwal et al., 2021] Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, Ben Lengerich, Rich Caruana, and Geoffrey E Hinton. Neural additive models: Interpretable machine learning with neural nets. Advances in Neural Information Processing Systems, 34:4699-4711, 2021.","title":"Neural additive models: Interpretable machine learning with neural nets","authors":"Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, Ben Lengerich, Rich Caruana, Geoffrey E Hinton","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Anand et al., 2015] Kartik Anand, Ben Craig, and Goetz Von Peter. Filling in the blanks: Network structure and in- terbank contagion. Quantitative Finance, 15(4):625-636, 2015.","title":"Filling in the blanks: Network structure and interbank contagion","authors":"Kartik Anand, Ben Craig, Goetz Von, Peter","year":"2015","venue":"Quantitative Finance","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Becker and Milbourn, 2011] Bo Becker and Todd Mil- bourn. How did increased competition affect credit rat- ings? Journal of financial economics, 101(3):493-514, 2011.","title":"Bo Becker and Todd Milbourn. How did increased competition affect credit ratings?","authors":"Milbourn Becker","year":"2011","venue":"Journal of financial economics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bhatore et al., 2020] Siddharth Bhatore, Lalit Mohan, and Y Raghu Reddy. Machine learning techniques for credit risk evaluation: a systematic literature review. Journal of Banking and Financial Technology, 4:111-138, 2020.","title":"Machine learning techniques for credit risk evaluation: a systematic literature review","authors":"Siddharth Bhatore, Lalit Mohan, Y Raghu Reddy","year":"2020","venue":"Journal of Banking and Financial Technology","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Brunnermeier, 2009] Markus K Brunnermeier. Deciphering the liquidity and credit crunch 2007-2008. Journal of Eco- nomic perspectives, 23(1):77-100, 2009.","title":"Deciphering the liquidity and credit crunch 2007-2008","authors":"Markus K Brunnermeier","year":"2009","venue":"Journal of Economic perspectives","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cheng et al., 2019] Dawei Cheng, Yi Tu, Zhen-Wei Ma, Zhibin Niu, and Liqing Zhang. Risk assessment for networked-guarantee loans using high-order graph atten- tion representation. In IJCAI, pages 5822-5828, 2019.","title":"Risk assessment for networked-guarantee loans using high-order graph attention representation","authors":"Dawei Cheng, Yi Tu, Zhen-Wei Ma, Zhibin Niu, Liqing Zhang","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/807"},{"position":8,"raw":"[Cheng et al., 2020] Dawei Cheng, Xiaoyang Wang, Ying Zhang, and Liqing Zhang. Risk guarantee prediction in networked-loans. In IJCAI International Joint Conference on Artificial Intelligence, 2020.","title":"Risk guarantee prediction in networked-loans","authors":"Dawei Cheng, Xiaoyang Wang, Ying Zhang, Liqing Zhang","year":"2020","venue":"IJCAI International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/618"},{"position":9,"raw":"[Cheng et al., 2021] Dawei Cheng, Chen Chen, Xiaoyang Wang, and Sheng Xiang. Efficient top-k vulnerable nodes detection in uncertain graphs. IEEE Transactions on Knowledge and Data Engineering, 2021.","title":"Efficient top-k vulnerable nodes detection in uncertain graphs","authors":"Dawei Cheng, Chen Chen, Xiaoyang Wang, Sheng Xiang","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cheng et al., 2022] Dawei Cheng, Zhibin Niu, Jie Li, and Changjun Jiang. Regulating systemic crises: Stemming the contagion risk in networked-loans through deep graph learning. IEEE Transactions on Knowledge and Data En- gineering, 2022.","title":"Regulating systemic crises: Stemming the contagion risk in networked-loans through deep graph learning","authors":"Dawei Cheng, Zhibin Niu, Jie Li, Changjun Jiang","year":"2022","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dai et al., 2018] Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. Adversarial attack on graph structured data. In International conference on ma- chine learning, pages 1115-1124. PMLR, 2018. [des Règlements Internationaux, 1992] Banque des Règlements Internationaux. Recent developments in international interbank relations. Working Group of the Central Banks of the GIO, 1992.","title":"Adversarial attack on graph structured data","authors":"Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, Le Song","year":"1992","venue":"Working Group of the Central Banks of the GIO","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dittrich, 2007] Fabian Dittrich. The credit rating industry: competition and regulation. Available at SSRN 991821, 2007.","title":"The credit rating industry: competition and regulation","authors":"Fabian Dittrich, Dittrich","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Elsinger et al., 2013] Helmut Elsinger, Alfred Lehar, and Martin Summer. Network models and systemic risk as- sessment. Handbook on Systemic Risk, 1(1):287-305, 2013.","title":"Network models and systemic risk assessment","authors":"Elsinger","year":"2013","venue":"Handbook on Systemic Risk","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Entezari et al., 2020] Negin Entezari, Saba A Al-Sayouri, Amirali Darvishzadeh, and Evangelos E Papalexakis. All you need is low (rank) defending against adversarial at- tacks on graphs. In Proceedings of the 13th International Conference on Web Search and Data Mining, pages 169- 177, 2020.","title":"All you need is low (rank) defending against adversarial attacks on graphs","authors":"Negin Entezari, Saba A Al-Sayouri, Amirali Darvishzadeh, Evangelos E Papalexakis","year":"2020","venue":"Proceedings of the 13th International Conference on Web Search and Data Mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Feng et al., 2022] Bojing Feng, Haonan Xu, Wenfang Xue, and Bindang Xue. Every corporation owns its structure: Corporate credit rating via graph neural networks. In Pat- tern Recognition and Computer Vision: 5th Chinese Con- ference, PRCV 2022, Shenzhen, China, November 4-7, 2022, Proceedings, Part I, pages 688-699. Springer, 2022.","title":"Every corporation owns its structure: Corporate credit rating via graph neural networks","authors":"Feng","year":"2022","venue":"Pattern Recognition and Computer Vision: 5th Chinese Conference, PRCV 2022","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Golbayani et al., 2020a] Parisa Golbayani, Ionut ¸Florescu, and Rupak Chatterjee. A comparative study of forecast- ing corporate credit ratings using neural networks, support vector machines, and decision trees. The North American Journal of Economics and Finance, 54:101251, 2020.","title":"Parisa Golbayani, Ionut ¸Florescu, and Rupak Chatterjee. A comparative study of forecasting corporate credit ratings using neural networks, support vector machines, and decision trees","authors":"Golbayani","year":"2020","venue":"The North American Journal of Economics and Finance","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Golbayani et al., 2020b] Parisa Golbayani, Dan Wang, and Ionut Florescu. Application of deep neural networks to assess corporate credit rating. arXiv preprint arXiv:2003.02334, 2020.","title":"Application of deep neural networks to assess corporate credit rating","authors":"Golbayani","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Gyntelberg and Wooldridge, 2008] Jacob Gyntelberg and Philip D Wooldridge. Interbank rate fixings during the re- cent turmoil. BIS Quarterly Review, March, 2008.","title":"Interbank rate fixings during the recent turmoil","authors":"Wooldridge Gyntelberg, Jacob Gyntelberg, Philip D Wooldridge","year":"2008","venue":"BIS Quarterly Review","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ioannidis et al., 2010] Christos Ioannidis, Fotios Pasiouras, and Constantin Zopounidis. Assessing bank soundness with classification techniques. Omega, 38(5):345-357, 2010.","title":"Assessing bank soundness with classification techniques","authors":"Christos Ioannidis, Fotios Pasiouras, Constantin Zopounidis","year":"2010","venue":"Omega","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jin et al., 2020] Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, and Jiliang Tang. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 66-74, 2020.","title":"Graph structure learning for robust graph neural networks","authors":"Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang","year":"2020","venue":"Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lee, 2007] Young-Chan Lee. Application of support vec- tor machines to corporate credit rating prediction. Expert Systems with Applications, 33(1):67-74, 2007.","title":"Application of support vector machines to corporate credit rating prediction","authors":"Young-Chan Lee","year":"2007","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Macchiati et al., 2022] Valentina Macchiati, Giuseppe Brandi, Tiziana Di Matteo, Daniela Paolotti, Guido Cal- darelli, and Giulio Cimini. Systemic liquidity contagion in the european interbank market. Journal of Economic Interaction and Coordination, 17(2):443-474, 2022.","title":"Systemic liquidity contagion in the european interbank market","authors":"Valentina Macchiati, Giuseppe Brandi, Tiziana Di Matteo, Daniela Paolotti, Guido Caldarelli, Giulio Cimini","year":"2022","venue":"Journal of Economic Interaction and Coordination","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[McPherson et al., 2001] Miller McPherson, Lynn Smith- Lovin, and James M Cook. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415- 444, 2001.","title":"Birds of a feather: Homophily in social networks","authors":"Mcpherson","year":"2001","venue":"Annual review of sociology","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Meng et al., 2017] Xiangfeng Meng, Yunhai Tong, Xinhai Liu, Yiren Chen, and Shaohua Tan. Netrating: Credit risk evaluation for loan guarantee chain in china. In Intelli- gence and Security Informatics: 12th Pacific Asia Work- shop, PAISI 2017, Jeju Island, South Korea, May 23, 2017, Proceedings 12, pages 99-108. Springer, 2017.","title":"Netrating: Credit risk evaluation for loan guarantee chain in china","authors":"Xiangfeng Meng, Yunhai Tong, Xinhai Liu, Yiren Chen, Shaohua Tan","year":"2017","venue":"Intelligence and Security Informatics: 12th Pacific Asia Workshop, PAISI 2017","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Nier et al., 2007] Erlend Nier, Jing Yang, Tanju Yorul- mazer, and Amadeo Alentorn. Network models and finan- cial stability. Journal of Economic Dynamics and Control, 31(6):2033-2060, 2007.","title":"Network models and financial stability","authors":"Erlend Nier, Jing Yang, Tanju Yorulmazer, Amadeo Alentorn","year":"2007","venue":"Journal of Economic Dynamics and Control","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Niu et al., 2020] Zhibin Niu, Runlin Li, Junqi Wu, Dawei Cheng, and Jiawan Zhang. iconviz: Interactive visual exploration of the default contagion risk of networked- guarantee loans. In 2020 IEEE conference on visual ana- lytics science and technology (VAST), pages 84-94. IEEE, 2020.","title":"iconviz: Interactive visual exploration of the default contagion risk of networkedguarantee loans","authors":"Zhibin Niu, Runlin Li, Junqi Wu, Dawei Cheng, Jiawan Zhang","year":"2020","venue":"IEEE conference on visual analytics science and technology (VAST)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sheldon et al., 1998] George Sheldon, Martin Maurer, et al. Interbank lending and systemic risk: An empirical analysis for switzerland. Revue suisse d economie politique et de statistique, 134:685-704, 1998.","title":"Interbank lending and systemic risk: An empirical analysis for switzerland","authors":"Sheldon","year":"1998","venue":"Revue suisse d economie politique et de statistique","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sun et al., 2022] Lichao Sun, Yingtong Dou, Carl Yang, Kai Zhang, Ji Wang, S Yu Philip, Lifang He, and Bo Li. Adversarial attack and defense on graph data: A survey. IEEE Transactions on Knowledge and Data Engineering, 2022.","title":"Adversarial attack and defense on graph data: A survey","authors":"Sun","year":"2022","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Tang et al., 2020] Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, and Suhang Wang. Transfer- ring robustness for graph neural network against poison- ing attacks. In Proceedings of the 13th international con- ference on web search and data mining, pages 600-608, 2020.","title":"Transferring robustness for graph neural network against poisoning attacks","authors":"Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang","year":"2020","venue":"Proceedings of the 13th international conference on web search and data mining","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Veličković et al., 2017] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wallis et al., 2019] Mark Wallis, Kuldeep Kumar, and Adrian Gepp. Credit rating forecasting using machine learning techniques. In Managerial perspectives on in- telligent big data analytics, pages 180-198. IGI Global, 2019.","title":"Credit rating forecasting using machine learning techniques","authors":"Mark Wallis, Kuldeep Kumar, Adrian Gepp","year":"2019","venue":"Managerial perspectives on intelligent big data analytics","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wu et al., 2019] Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, and Liming Zhu. Adversarial examples on graph data: Deep insights into attack and de- fense. arXiv preprint arXiv:1903.01610, 2019.","title":"Adversarial examples on graph data: Deep insights into attack and defense","authors":"Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhu et al., 2019] Dingyuan Zhu, Ziwei Zhang, Peng Cui, and Wenwu Zhu. Robust graph convolutional networks against adversarial attacks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1399-1407, 2019.","title":"Robust graph convolutional networks against adversarial attacks","authors":"Dingyuan Zhu, Ziwei Zhang, Peng Cui, Wenwu Zhu","year":"2019","venue":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zügner et al., 2018] Daniel Zügner, Amir Akbarnejad, and Stephan Günnemann. Adversarial attacks on neural net- works for graph data. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discov- ery & data mining, pages 2847-2856, 2018.","title":"Adversarial attacks on neural networks for graph data","authors":"Daniel Zügner, Amir Akbarnejad, Stephan Günnemann","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining","doi":null,"url":null,"internal_url":"/proceedings/2019/872"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}