InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic Features

no code implementations • 14 Oct 2022 • Mingfu Xue, Xin Wang, Yinghao Wu, Shifeng Ni, Yushu Zhang, Weiqiang Liu

Since the intrinsic feature is composed of unique interpretation of the model's decision, the intrinsic feature can be regarded as fingerprint of the model.

Explainable artificial intelligence

Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks

no code implementations • 31 Jan 2022 • Mingfu Xue, Shifeng Ni, Yinghao Wu, Yushu Zhang, Jian Wang, Weiqiang Liu

Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks.

Backdoor Attack backdoor defense