Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability

Abstract

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.

arXiv commentAccepted to ICML 2021

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• How transferable are features in deep neural networks?
• Character-level Convolutional Networks for Text Classification
• Learning Transferable Features with Deep Adaptation Networks
• Ensemble Adversarial Training: Attacks and Defenses
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Adversarial Discriminative Domain Adaptation
• The Space of Transferable Adversarial Examples
• What makes ImageNet good for transfer learning?
• Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
• Improving Adversarial Robustness of Ensembles with Diversity Training
• Cross-Domain Transferability of Adversarial Perturbations