Free Delivery on orders above $50 for our US and Europe customers
1 2

Elevation of Machine Learning Security Game

£24.00

Description

Created by Elias Brattli Sørensen, Elevation of MLSec is a threat modeling card game inspired by Adam Shostack’s Elevation of Privilege game, and based on the risk framework published by the Berryville Institute of Machine Learning (BIML). 

These playing cards portray risks associated with Machine Learning systems that have been identified by research groups. 

The cards are arranged in 4 threat categories (or "suits"). The ten components from the BIML-78 risk analysis are mapped to these 4 suits: Dataset risks (Raw, Training, Assembly), Model risks (Algorithm, Evaluation, Model), Input risks and Output risks.

The inference risks and system wide risks are applied to categories where the individual risk fits best. There are also a few LLM risks to give the deck a little flavour. 

Elevation of MLSec is © 2024 Kantega AS

Bulk Pricing

Automatically applied at checkout:

Buy Discount
5 or more decks 10% off
10 or more decks 15% off
20 or more decks 20% off
30 or more decks 30% off

Outcome

Identify Machine Learning work that needs doing earlier in the project lifecycle. Defuse difficult relationships. Build trust. Bring teams together in peace and harmony.

Made by Agile Stationery

Experts in delivering the right kind of conversations. Slick cards in robust boxes. The best there is outside the casinos.

Specifications
  • Suits
    Dataset risks (Raw, Training, Assembly), Model risks (Algorithm, Evaluation, Model), Input risks , Output risks
  • # Cards
    68
  • Created by
    Elias Brattli Sørensen

Try a branded version

If you'd like to encourage the use of this technique within your team or organisation, a branded deck is a great way to demonstrate your support and commitment to the process.

How to play?

  • Set up

    Start by creating a visible model of the ML system you’ll be threat modelling, this could be a lifecycle, pipeline, or any system with an ML component.

  • Deal the cards

    Remove the instruction, strategy, and threat summary cards. Just keep the threat cards.

    Shuffle and deal the entire deck to players in small groups (3–6 people per deck).

  • Let the game begin

    The player with the lowest Input Risk card goes first. Others must follow suit (the risk category) if they can.

  • Winning

    Each round, players play one card, matching the suit (risk type) of the first card if possible. The highest card wins, unless a Dataset Risk card is played, as these are always trump.

    Scoring: +1 for a relevant threat, +1 for winning the trick.

  • Additional rules

    Aces let players introduce a new, unlisted threat based on the system, showing insight and creativity.

    When all cards have been played, the player with the most points wins.

Hybrid teams? No problem

Play our threat modeling games remotely
with the power of physical cards!

Croupier
Back to top