Haizhong Zheng

In this study, we introduce a novel sybil detection approach by exploiting the fundamental mobility patterns that separate real users from sybil ones. Expand

We propose a novel adversarial training method called ATTA (Adversarial Training with Transferable Adversarial examples) that can enhance the robustness of trained models and greatly improve the training efficiency by accumulating adversarial perturbations through epochs. Expand

A three-phase methodology to detect click farming on content-generated social networks. Expand

We define, characterize, and detect elite Sybil attacks, which recruits organically highly-rated accounts to generate seemingly-trustworthy and realistic-looking reviews on popular URSN services. Expand

We use the Louvain community detection method to detect click farming in content-generated social networks. Expand

We propose a new approach, robust feature augmentation, as a component of standard machine learning techniques. Expand

We evaluate the interpretability robustness of SEMs and show that explanations provided by SEMs as currently proposed are not robust to adversarial inputs. Expand