Mike Afton

Model · Image classification

datapoisoning-detector-v1-tiny

Mike Afton

Original diagrams for this release. Editable SVG versions: architecture · inference and distillation. Weights and completed test results are included in this release bundle. The detector compares encoder blocks 1, 2 and 3 with the final posterior-mean representation of a frozen FLUX.2 VAE. Each stream is projected to an 8 × 8 token grid. The three early-to-final differences are fused with all four feature streams before transformer classification. Inputs are native-resolution 128 × 128 RGB crops with a central 96 × 96 active region. The VAE decoder and generative FLUX transformer are not used. The training run excludes CelebA-HQ from training, validation and patch caches; it is used only…

Model · Image classification

datapoisoning-detector-v1-small

Mike Afton

Original diagrams for this release. Editable SVG versions: architecture · inference and distillation. Weights and completed test results are included in this release bundle. The detector compares encoder blocks 1, 2 and 3 with the final posterior-mean representation of a frozen FLUX.2 VAE. Each stream is projected to an 8 × 8 token grid. The three early-to-final differences are fused with all four feature streams before transformer classification. Inputs are native-resolution 128 × 128 RGB crops with a central 96 × 96 active region. The VAE decoder and generative FLUX transformer are not used. The training run excludes CelebA-HQ from training, validation and patch caches; it is used only…

Model · Image classification

datapoisoning-detector-v1-medium

Mike Afton

Original diagrams for this release. Editable SVG versions: architecture · inference and distillation. Weights and completed test results are included in this release bundle. The detector compares encoder blocks 1, 2 and 3 with the final posterior-mean representation of a frozen FLUX.2 VAE. Each stream is projected to an 8 × 8 token grid. The three early-to-final differences are fused with all four feature streams before transformer classification. Inputs are native-resolution 128 × 128 RGB crops with a central 96 × 96 active region. The VAE decoder and generative FLUX transformer are not used. The training run excludes CelebA-HQ from training, validation and patch caches; it is used only…

Model · Image classification

datapoisoning-detector-v1-large

Mike Afton

Original diagrams for this release. Editable SVG versions: architecture · inference and distillation. Weights and completed test results are included in this release bundle. The detector compares encoder blocks 1, 2 and 3 with the final posterior-mean representation of a frozen FLUX.2 VAE. Each stream is projected to an 8 × 8 token grid. The three early-to-final differences are fused with all four feature streams before transformer classification. Inputs are native-resolution 128 × 128 RGB crops with a central 96 × 96 active region. The VAE decoder and generative FLUX transformer are not used. The training run excludes CelebA-HQ from training, validation and patch caches; it is used only…