A Survey of Deep Learning Models for Structural Code Understanding

1 code implementation • 3 May 2022 • Ruoting Wu, Yuxin Zhang, Qibiao Peng, Liang Chen, Zibin Zheng

In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights.

Neighboring Backdoor Attacks on Graph Convolutional Network

no code implementations • 17 Jan 2022 • Liang Chen, Qibiao Peng, Jintang Li, Yang Liu, Jiawei Chen, Yong Li, Zibin Zheng

To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node.

Backdoor Attack

Understanding Structural Vulnerability in Graph Convolutional Networks

1 code implementation • 13 Aug 2021 • Liang Chen, Jintang Li, Qibiao Peng, Yang Liu, Zibin Zheng, Carl Yang

In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i. e., the weighted mean) of GCNs.