Similarity of Neural Architectures using Adversarial Attack Transferability

Understand

In recent years, many deep neural architectures have been developed for image classification.

• Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious.
• To address this question, we aim to design a quantitative and scalable similarity measure between neural architectures.
• We propose Similarity by Attack Transferability (SAT) from the observation that adversarial attack transferability contains information related to input gradients and decision boundaries widely used to understand model behaviors.