Skip to content

Repository files navigation

Autostego

image

Autostego is a small research game between Alice, who hides a payload, and Eve, who tries to spot it. A round has two six-hour turns. Alice freezes an embedding method, Eve trains against it and freezes a detector, and then the human scores the pair on private images.

Alice wants Eve at 50% balanced accuracy. Eve wants the number as high as she can get it.

The repo starts with HILL, SRNet, and one reproducible recipe for each player. Either player may replace them, as long as the submitted artifact can be rebuilt from the accompanying recipe.

AGENTS.md describes how a round runs. ALICE.md and EVE.md are the two turn briefs.

Setup

The project expects Python 3.12 and uv.

uv sync --frozen

Alice's artifact

alice.py embeds the public training and development images.

AUTOSTEGO_EMBED_KEY='local-research-key' uv run python alice.py

Alice hands over one artifact containing the embedded public dataset and the committed alice.py that made it.

Eve's artifact

eve.py trains the current detector recipe. It runs directly on one GPU or with torchrun on a multi-GPU game machine.

uv run python eve.py
uv run torchrun --standalone --nproc_per_node=8 eve.py

Eve hands over one artifact containing the frozen detector and the committed eve.py that trained it.

About

No description, website, or topics provided.

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages