Qi Tan (College of Computer Science and Software Engineering, Shenzhen University), Yi Zhao (School of Cyberspace Science and Technology, Beijing Institute of Technology), Laizhong Cui (College of Computer Science and Software Engineering, Shenzhen University), Qi Li (Institute for Network Science and Cyberspace, Tsinghua University), Ming Zhu (Department of Computer Science and Technology, Tsinghua University), Xing Fu (Ant Group), Weiqiang Wang (Ant Group), Xiaotong Lin (Ant Group), Ke Xu (Department of Computer Science and Technology, Tsinghua University)

Machine learning (ML)-based fraud detection systems are widely employed by enterprises to reduce economic losses from fraudulent activities. However, fraudsters are intelligent and evolve rapidly, employing advanced techniques to falsify the features of transactions to evade the detection system. Worse still, since these falsification processes are not restricted to small intervals, existing robustness enhancement methods based on small-scale perturbations are ineffective. Detecting unrestrictedly perturbed fraudulent activities, which significantly increases uncertainties in fraud detection, is still an open problem.

To resolve this issue, we propose GAMER, a robust fraud detection system based on two-player game, achieving both high accuracy and strong robustness in detecting fraudulent activities. Specifically, GAMER leverages feature selection to proactively combat intelligent fraudsters in fraud detection (i.e., selecting fewer features to reduce the combinations of feature falsification), and innovatively formulates the detecting process as a two-player game. By solving the equilibrium of the two-player game, GAMER calculates the optimal probability for feature selection, which takes into account all possible falsification strategies of the fraudsters. The equilibrium-based selection probability not only minimizes the profits obtained by fraudsters, demotivating them to launch falsification; but also enables the system to select robust features (i.e., the features that are less likely to be falsified) in detecting fraudulent activities, enhancing the robustness of the system in fraud detection. Our theoretical and experimental results validate the properties of deterrence and robustness enhancement. Moreover, experiments on real-world attacks suffered by the world’s leading online payment enterprise demonstrate that GAMER outperforms traditional techniques of robustness enhancement, which increases the F1 score by 67.5% on average for two-month fraud detection.

View More Papers

ReFuzz: Reusing Tests for Processor Fuzzing with Contextual Bandits

Chen Chen (Texas A&M University, USA), Zaiyan Xu (Texas A&M University, USA), Mohamadreza Rostami (Technische Universitat Darmstadt, Germany), David Liu (Texas A&M University, USA), Dileep Kalathil (Texas A&M University, USA), Ahmad-Reza Sadeghi (Technische Universitat Darmstadt, Germany), Jeyavijayan (JV) Rajendran (Texas A&M University, USA)

Read More

When Focus Enhances Utility: Target Range LDP Frequency Estimation...

Bo Jiang (TikTok Inc.), Wanrong Zhang (TikTok Inc.), Donghang Lu (TikTok Inc.), Jian Du (TikTok Inc.), Qiang Yan (TikTok Inc.)

Read More

UIEE: Secure and Efficient User-space Isolated Execution Environment for...

Huaiyu Yan (Southeast University), Zhen Ling (Southeast University), Xuandong Chen (Southeast University), Xinhui Shao (Southeast University, City University of Hong Kong), Yier Jin (University of Science and Technology of China), Haobo Li (Southeast University), Ming Yang (Southeast University), Ping Jiang (Southeast University), Junzhou Luo (Southeast University, Fuyao University of Science and Technology)

Read More