162  counterfit(1) - Kailash Tool Reference

162.1 counterfit

counterfit - Counterfit — CLI automation layer for assessing the security of ML models (pinned reference posture; upstream dormant since 2025-07).

Layer ATTACK
Category a-05-model-extraction-inversion
Safety class requires-target
Licence MIT
Upstream github.com/Azure/counterfit

162.1.1 NAME

counterfit - Counterfit — CLI automation layer for assessing the security of ML models (pinned reference posture; upstream dormant since 2025-07).

162.1.2 SYNOPSIS & usage

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

                          __            _____ __
  _________  __  ______  / /____  _____/ __(_) /_
 / ___/ __ \/ / / / __ \/ __/ _ \/ ___/ /_/ / __/
/ /__/ /_/ / /_/ / / / / /_/  __/ /  / __/ / /
\___/\____/\__,_/_/ /_/\__/\___/_/  /_/ /_/\__/

                                        #ATML

---------------------------------------------------
    az container exec --resource-group <RESOURCE_GROUP> --name counterfit --exec-command '/bin/bash'

162.1.3 DESCRIPTION (upstream)

About | Getting Started | Acknowledgments | Contributing | Trademarks | Contact Us __ _____ __ _________ __ ______ / /____ _____/ () / / _/ __ / / / / __ / / _ / _/ // / / / // // / // / / / / // / / / / / / _/__/_,// //__/___// // //_/ Counterfit is a generic automation layer for assessing the security of machine learning systems. It brings several existing adversarial frameworks under one tool, or allows users to create their own. To run this tool, you need to have the following softwares installed: 1. Python 3.8 or higher 2. Minicond

162.1.4 CONFIGURATION (detected)

Config-surface markers detected in the upstream README (3 matches, e.g. tests.yaml, tests.yaml). A full config reference page for this tool is queued under the config-page policy — this line is the detection record, not the page.

162.1.5 SEE ALSO

ref: v1.1.0-unstable-2025-07-18 - verified 2026-10-14