Beyond the individual: An improved telecom fraud detection approach based on latent synergy graph learning.

The development of telecom technology not only facilitates social interactions but also inevitably provides the breeding ground for telecom fraud crimes. However, telecom fraud detection is a challenging task as fraudsters tend to commit co-fraud and disguise themselves within the mass of benign ones. Previous approaches work by unearthing differences in calling sequential patterns between independent fraudsters, but they may ignore synergic fraud patterns and oversimplify fraudulent behaviors. Fortunately, graph-like data formed by traceable telecom interaction provides opportunities for graph neural network (GNN)-based telecom fraud detection methods. Therefore, we develop a latent synergy graph (LSG) learning-based telecom fraud detector, named LSG-FD, to model both sequential and interactive fraudulent behaviors. Specifically, LSG-FD introduces (1) a multi-view LSG extractor to reconstruct synergy relationship-oriented graphs from the meta-interaction graph based on second-order proximity assumption; (2) an LSTM-based calling behavior encoder to capture the sequential patterns from the perspective of local individuals; (3) a dual-channel based graph learning module to alleviate the disassortativity issue (caused by the camouflages of fraudsters) by incorporating the dual-channel frequency filters and the learnable controller to adaptively aggregate high- and low-frequency information from their neighbors; (4) an imbalance-resistant model trainer to remedy the graph imbalance issue by developing a label-aware sampler. Experiment results on the telecom fraud dataset and another two widely used fraud datasets have verified the effectiveness of our model.

[δ¹5N-NO3⁻ and δ¹8O-NO3⁻ Tracing of Nitrate Sources in Beijing Urban Rivers].

In order to quantitatively identify sources of nitrate pollution in Beijing urban area and provide effective guidance for relevant departments to control the pollution of Beijing rivers, δ¹5N-NO3⁻ and δ¹8O-NO3⁻ isotope tracing method was used to analyze the composition of nitrogen and oxygen stable isotopes from nitrate in Beijing urban river. Besides, stable isotope mixing model was adopted to track nitrogen sources of nitrate in Beijing urban rivers and the contribution rates of respective pollution sources were evaluated. The results showed that: (1) NO3⁻-N pollution was the main inorganic nitrogen pollution in Beijing rivers and pollution of downstream was more serious than that of upstream. (2) δ¹5N-NO3⁻ in Beijing urban surface rivers was in range of 6.26 per thousand-24.94 per thousand, while δ¹8O-NO3⁻ ranged -0.41 per thousand-11.74 per thousand; δ¹5N-NO3⁻ increased from upstream to downstream along the flow of the surface water. (3) The nitrate pollution composition of Beijing rivers could be gained from the stable isotope mixing model. The average contribution rates of manure and sewage, soil nitrate and atmospheric deposition were 61.2%, 31.5% and 7.3%, respectively.