Multi-head Uncertainty Inference for Adversarial Attack Detection

no code implementations • 20 Dec 2022 • YuQi Yang, Songyun Yang, Jiyang Xie. Zhongwei Si, Kai Guo, Ke Zhang, Kongming Liang

We adopt a multi-head architecture with multiple prediction heads (i. e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI.

Adversarial Attack Detection Adversarial Defense