Patch Vestiges in the Adversarial Examples Against Vision Transformer Can Be Leveraged for Adversarial Detection

no code implementations • AAAI Workshop AdvML 2022 • Juzheng Li

The experiments show that the performance of the simple classifier can even match some recent adversarial detection methods, suggesting that when trying to attack ViT or detect the AEs against ViT, Patch Vestiges are worth considering about as a critical factor.

Textbook Question Answering Under Instructor Guidance With Memory Networks

1 code implementation • CVPR 2018 • Juzheng Li, Hang Su, Jun Zhu, Siyu Wang, Bo Zhang

The machine thus performs as an instructor to extract the essay-level contradictions as the Guidance.

Question Answering

Discriminative Deep Random Walk for Network Classification

no code implementations • ACL 2016 • Juzheng Li, Jun Zhu, Bo Zhang

Anomaly Detection Classification +2