Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks
This addresses the robustness problem for CNN users in image classification, but it is incremental as it builds on existing adversarial attack research.
The paper tackles the vulnerability of Convolutional Neural Networks (CNNs) to non-uniform illumination attacks by introducing a novel attack technique that uses varying illumination masks, resulting in a substantial decline in classification accuracy for models like VGG and ResNet, and proposes a defense strategy that enhances performance by including attacked images in training.
Convolutional Neural Networks (CNNs) have made remarkable strides; however, they remain susceptible to vulnerabilities, particularly in the face of minor image perturbations that humans can easily recognize. This weakness, often termed as 'attacks', underscores the limited robustness of CNNs and the need for research into fortifying their resistance against such manipulations. This study introduces a novel Non-Uniform Illumination (NUI) attack technique, where images are subtly altered using varying NUI masks. Extensive experiments are conducted on widely-accepted datasets including CIFAR10, TinyImageNet, and CalTech256, focusing on image classification with 12 different NUI attack models. The resilience of VGG, ResNet, MobilenetV3-small and InceptionV3 models against NUI attacks are evaluated. Our results show a substantial decline in the CNN models' classification accuracy when subjected to NUI attacks, indicating their vulnerability under non-uniform illumination. To mitigate this, a defense strategy is proposed, including NUI-attacked images, generated through the new NUI transformation, into the training set. The results demonstrate a significant enhancement in CNN model performance when confronted with perturbed images affected by NUI attacks. This strategy seeks to bolster CNN models' resilience against NUI attacks.