Pre-trained and sample-transferable perturbation based adversarial neuron manipulation: revealing the risks of transfer learning in remote sensing

• Main Author: Tian, Xingjian
• Other Authors: Wen Bihan
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Adversarial attack; Transfer learning; Deep learning; Remote sensing; Image classification; Neuron manipulation; Robustness of AI
• Online Access: https://hdl.handle.net/10356/180881
• Institution: Nanyang Technological University

The classification of remote sensing images has been revolutionized by the advent of deep learning, particularly through the application of transfer learning techniques. However, the susceptibility of these models to adversarial attacks poses significant challenges. Existing adversarial attacks a...