| Abstract | This dataset comprises combined gradient maps from sixteen pretrained convolutional and transformer-based networks for use with Multi-Targeted Gradient Training (MTGT). The combined gradients were optimized for a cyan (488 nm) Wavelength-Specific Map Attack. Each example corresponds to an original ImageNet-1K training or validation image, and the resulting combined gradient is stored as a single-channel (1 X 224 X 224) map. The combined gradient was computed by averaging the cross-entropy gradient of each network with respect to the true class, multiplying channel-wise by the RGB translation of a 488 nm cyan laser, and summing across channels. The ensemble includes AlexNet, DenseNet-161, EfficientNet-B0, GoogLeNet, MNASNet (depth multiplier 0.5), MobileNetV2, MobileNetV3-Small, RegNetY-800MF, ResNet-50, ResNeXt-50 (32 X 4d), ShuffleNetV2-x0.5, SqueezeNet1.1, VGG-16, and Wide ResNet-50 v2, all sourced from the PyTorch Model Library and trained using a common preprocessing scheme in which the shortest side of the input was resized to 256 pixels while preserving aspect ratio, followed by a 224 X 224 center crop. The remaining two models, ConvNeXt Base and MaxViT-T, were also sourced from the PyTorch Model Library but used a different original preprocessing scheme, so they were fine-tuned to align with the rest of the ensemble. |
