Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
This work addresses the need for better insights into transfer learning and adversarial robustness, offering bidirectional indicators that could guide future research in these areas, though it is incremental in linking two known phenomena.
The paper tackles the problem of understanding factors affecting knowledge transferability by analyzing its connections with adversarial transferability, showing a positive correlation through theoretical studies and extensive experiments on diverse datasets.
Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand the factors affecting knowledge transferability. In this paper, as the first work, we analyze and demonstrate the connections between knowledge transferability and another important phenomenon--adversarial transferability, \emph{i.e.}, adversarial examples generated against one model can be transferred to attack other models. Our theoretical studies show that adversarial transferability indicates knowledge transferability and vice versa. Moreover, based on the theoretical insights, we propose two practical adversarial transferability metrics to characterize this process, serving as bidirectional indicators between adversarial and knowledge transferability. We conduct extensive experiments for different scenarios on diverse datasets, showing a positive correlation between adversarial transferability and knowledge transferability. Our findings will shed light on future research about effective knowledge transfer learning and adversarial transferability analyses.