4 papers
SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
Lingyu Du, Yupei Liu, Jinyuan Jia +1
Gaze estimation models are widely used in applications such as driver attention monitoring and human-computer interaction. While many methods for gaze estimation exist, they rely h…
Defending Deep Regression Models against Backdoor Attacks
Lingyu Du, Yupei Liu, Jinyuan Jia +1
Deep regression models are used in a wide variety of safety-critical applications, but are vulnerable to backdoor attacks. Although many defenses have been proposed for classificat…
Stealing Training Graphs from Graph Neural Networks
Minhua Lin, Enyan Dai, Junjie Xu +3
Graph Neural Networks (GNNs) have shown promising results in modeling graphs in various tasks. The training of GNNs, especially on specialized tasks such as bioinformatics, demands…
PrivateGaze: Preserving User Privacy in Black-box Mobile Gaze Tracking Services
Lingyu Du, Jinyuan Jia, Xucong Zhang +1
Eye gaze contains rich information about human attention and cognitive processes. This capability makes the underlying technology, known as gaze tracking, a critical enabler for ma…