10 citations · 11 across the 2 of their papers we have counts for
2 papers
cs.LG2022★ 1 cited
Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Weiqi Peng, Jinghui Chen
Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digita…
cs.CV2020★ 10 cited
One-pixel Signature: Characterizing CNN Models for Backdoor Detection
Shanjiaoyang Huang, Weiqi Peng, Zhiwei Jia +1
We tackle the convolution neural networks (CNNs) backdoor detection problem by proposing a new representation called one-pixel signature. Our task is to detect/classify if a CNN mo…