Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
This work addresses the vulnerability of object detectors to adversarial attacks, offering a more efficient and effective approach for security testing, though it appears incremental as it builds on existing adversarial example research.
The paper tackles the problem of generating adversarial examples for object detectors by proposing a method that uses higher-level semantic information to create local perturbations, specifically for anchor-free detectors, resulting in less computational intensity and higher black-box and transfer attack performance.
The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they generate globally perturbation on the whole image, which is unnecessary. In our work, we leverage higher-level semantic information to generate high aggressive local perturbations for anchor-free object detectors. As a result, it is less computationally intensive and achieves a higher black-box attack as well as transferring attack performance. The adversarial examples generated by our method are not only capable of attacking anchor-free object detectors, but also able to be transferred to attack anchor-based object detector.