Year: 2024
Type: preprint
Abstract: Local feature extractors are the cornerstone of many computer vision tasks. However, their vulnerability to adversarial attacks can significantly compromise their effectiveness. This paper discusses approaches to attack sophisticated local feature extraction algorithms and models to achieve two distinct goals: (1) forcing a match between originally non-matching image regions, and (2) preventing a match between originally matching regions. At the end of the paper, we discuss the performance and drawbacks of different patch generation methods.
Source: arXiv (Cornell University)
Authors: Pao, Yu Wen, Lai, Li Chang, Lin, Hong-Yi
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4399657494