172  knockoffnets(1) - Kailash Tool Reference

172.1 knockoffnets

knockoffnets - Knockoff Nets — black-box model functionality stealing via transfer-set queries on a substitute data budget.

Layer ATTACK
Category a-05-model-extraction-inversion
Safety class requires-target
Licence LGPL-3.0
Upstream github.com/tribhuvanesh/knockoffnets

172.1.1 NAME

knockoffnets - Knockoff Nets — black-box model functionality stealing via transfer-set queries on a substitute data budget.

172.1.2 SYNOPSIS & usage

Derived from the upstream README at generation time; verify against --help where the tool is installed.

$ conda env create -f environment.yml   # anaconda; or
$ pip install -r requirements.txt       # pip
@inproceedings{orekondy19knockoff,
    TITLE = {Knockoff Nets: Stealing Functionality of Black-Box Models},
    AUTHOR = {Orekondy, Tribhuvanesh and Schiele, Bernt and Fritz, Mario},
    YEAR = {2019},
    BOOKTITLE = {CVPR},
}

172.1.3 DESCRIPTION (upstream)

Tribhuvanesh Orekondy, Bernt Schiele Mario Fritz Max Planck Institute for Informatics Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of such “victim” models based solely on blackbox interactions: image in, predictions out. In contrast to prior work, we present an adversary lacking knowledge of train/test data used by the model, its internals, and semantics over model outputs. We formulate model functionality stealing as a two-step approach: (i) querying a set of input images to the blackbox model to obtain predictions; and (ii) training a “knockoff” with quer

172.1.4 SEE ALSO

ref: pin - verified 2026-10-14