Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

no code implementations • ICLR 2022 • Weiqi Peng, Jinghui Chen

In particular, we propose adversarial invertible transformation, that can be viewed as a mapping from image to image, to slightly modify data samples so that they become "unlearnable" by machine learning models with negligible loss of visual features.

One-pixel Signature: Characterizing CNN Models for Backdoor Detection

no code implementations • ECCV 2020 • Shanjiaoyang Huang, Weiqi Peng, Zhiwei Jia, Zhuowen Tu

One-pixel signature is a general representation that can be used to characterize CNN models beyond backdoor detection.