Adversarial Color Film: Effective Physical-World Attack to DNNs
This addresses a gap in camera-based physical adversarial attacks, posing a threat to vision-based systems, though it is incremental as it builds on existing adversarial attack concepts.
The paper tackles the problem of physical-world adversarial attacks on deep neural networks by proposing Adversarial Color Film (AdvCF), which manipulates color film parameters to achieve effective attacks in both digital and physical environments, with strong transferability enabling black-box attacks.
It is well known that the performance of deep neural networks (DNNs) is susceptible to subtle interference. So far, camera-based physical adversarial attacks haven't gotten much attention, but it is the vacancy of physical attack. In this paper, we propose a simple and efficient camera-based physical attack called Adversarial Color Film (AdvCF), which manipulates the physical parameters of color film to perform attacks. Carefully designed experiments show the effectiveness of the proposed method in both digital and physical environments. In addition, experimental results show that the adversarial samples generated by AdvCF have excellent performance in attack transferability, which enables AdvCF effective black-box attacks. At the same time, we give the guidance of defense against AdvCF by means of adversarial training. Finally, we look into AdvCF's threat to future vision-based systems and propose some promising mentality for camera-based physical attacks.