A Statistical Physics Perspective: Understanding the Causality Behind Convolutional Neural Network Adversarial Vulnerability.
IEEE Trans Neural Netw Learn Syst
; PP2024 Feb 07.
Article
en En
| MEDLINE
| ID: mdl-38324429
ABSTRACT
The adversarial vulnerability of convolutional neural networks (CNNs) refers to the performance degradation of CNNs under adversarial attacks, leading to incorrect decisions. However, the causes of adversarial vulnerability in CNNs remain unknown. To address this issue, we propose a unique cross-scale analytical approach from a statistical physics perspective. It reveals that the huge amount of nonlinear effects inherent in CNNs is the fundamental cause for the formation and evolution of system vulnerability. Vulnerability is spontaneously formed on the macroscopic level after the symmetry of the system is broken through the nonlinear interaction between microscopic state order parameters. We develop a cascade failure algorithm, visualizing how micro perturbations on neurons' activation can cascade and influence macro decision paths. Our empirical results demonstrate the interplay between microlevel activation maps and macrolevel decision-making and provide a statistical physics perspective to understand the causality behind CNN vulnerability. Our work will help subsequent research to improve the adversarial robustness of CNNs.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Tipo de estudio:
Etiology_studies
Idioma:
En
Revista:
IEEE Trans Neural Netw Learn Syst
Año:
2024
Tipo del documento:
Article