CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
This addresses security concerns for real-world applications relying on object detection, such as autonomous vehicles or surveillance, by exposing vulnerabilities to adversarial attacks.
The paper tackles the vulnerability of deep neural network-based object detectors by proposing a contextual camouflage attack (CCA) algorithm, which uses evolutionary search and adversarial machine learning in a simulated environment to create effective camouflage patterns across various conditions, showing effectiveness against most state-of-the-art detectors.
Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea contextual camouflage attack (CCA for short) algorithm to in-fluence the performance of object detectors. In this paper, we usean evolutionary search strategy and adversarial machine learningin interactions with a photo-realistic simulated environment tofind camouflage patterns that are effective over a huge varietyof object locations, camera poses, and lighting conditions. Theproposed camouflages are validated effective to most of the state-of-the-art object detectors.