Date
Publisher
arXiv
This paper, submitted to the special track on resources for teaching AI in
K-12, presents an eXplainable AI (XAI)-based classroom game "Breakable Machine"
for teaching critical, transformative AI literacy through adversarial play and
interrogation of AI systems. Designed for learners aged 10-15, the game invites
students to spoof an image classifier by manipulating their appearance or
environment in order to trigger high-confidence misclassifications. Rather than
focusing on building AI models, this activity centers on breaking them-exposing
their brittleness, bias, and vulnerability through hands-on, embodied
experimentation. The game includes an XAI view to help students visualize
feature saliency, revealing how models attend to specific visual cues. A shared
classroom leaderboard fosters collaborative inquiry and comparison of
strategies, turning the classroom into a site for collective sensemaking. This
approach reframes AI education by treating model failure and misclassification
not as problems to be debugged, but as pedagogically rich opportunities to
interrogate AI as a sociotechnical system. In doing so, the game supports
students in developing data agency, ethical awareness, and a critical stance
toward AI systems increasingly embedded in everyday life. The game and its
source code are freely available.
Study at a glance
- Question: How can a game focused on tricking AI help students understand its weaknesses and limitations?
- Setting and data: K–12 classrooms, designed for learners aged 10–15
- Method: Description of a classroom game
Why it matters
Instead of only building models and debugging errors, students need to interrogate AI systems increasingly embedded in everyday life. They need opportunities to examine model failures to uncover AI's brittleness, bias, and vulnerability.
Key findings
- For students aged 10 to 15, actively tricking an image classifier supports the development of ethical awareness, data agency, and critical views toward AI systems.
- Visual explanations help students see the specific image cues an AI model relies on when making high-confidence classification errors.
- A shared classroom leaderboard fosters collaborative inquiry, helping students compare strategies and make sense of AI systems together.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Study design
