Combined Cross-Entropy Gradients From Diverse Sources For MTGT With Cyan WSMA

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 (1×224×224) 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 (32×4d), 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 its aspect ratio, followed by a 224 × 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.