Adversarial Patch for 3D Local Feature Extractor
This addresses security risks in computer vision systems for applications relying on feature matching, but it is incremental as it builds on existing adversarial attack methods.
This paper tackles the vulnerability of local feature extractors in computer vision by developing adversarial patch attacks to force matches between non-matching regions and prevent matches between matching regions, achieving specific attack goals with discussed performance metrics.
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.