Gang Liang
Papers
1
Total Citations
32
H-Index
1
About
Gang Liang is a prominent researcher in computational social network analysis, with a primary focus on detecting malicious and deceptive behaviors in online platforms. His work centers on developing advanced graph-based machine learning models to identify fake accounts, bots, and coordinated inauthentic activity, addressing critical challenges in cybersecurity and trust on social media. Liang’s most influential contribution is the "SybilFlyover" model, a heterogeneous graph-based framework for fake account detection, which has garnered 32 citations since its publication in 2022. This work stands out for its innovative use of multi-relational graph structures to capture complex interaction patterns among users, outperforming traditional homogeneous graph approaches. Beyond this, Liang has contributed to the broader field of graph neural networks and anomaly detection, with his research cited in top-tier venues like IEEE Transactions on Knowledge and Data Engineering. His achievements include developing scalable algorithms that balance detection accuracy with computational efficiency, making them practical for real-world deployment. Liang’s work is essential reading for researchers tackling online fraud, social bot detection, and graph-based security analytics.
Research Focus
Key Achievements
Top Papers
- 1