Our scheme constructs a composite deep learning model from the target GAN and a classifier.
Based on this property, we identify the discriminative areas of a given clean example easily for local perturbations.
In this paper, we investigate the effectiveness of data augmentation techniques in mitigating backdoor attacks and enhancing DL models' robustness.
Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.
In this paper, we propose a novel watermark removal attack from a different perspective.
In this paper, we design Top-DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems.
This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment.
However, there are currently no satisfactory solutions with strong efficiency and security in decentralized systems.