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 an adversarial classroom game help students develop critical AI literacy by spoofing an image classifier?
- Setting and data: Learners aged 10–15; sample size and location not stated in the abstract.
- Method: System development of a classroom game and learning activity.
Why it matters
Teaching AI literacy often focuses on building models rather than interrogating their brittleness, bias, and vulnerability as sociotechnical systems increasingly embedded in everyday life.
Key findings
- Manipulating appearance or environment allows students to intentionally trigger high-confidence misclassifications, exposing model brittleness and bias through embodied experimentation.
- Visualizing feature saliency through an explainable AI view reveals to students how models attend to specific visual cues.
- A shared classroom leaderboard fosters collaborative inquiry and comparison of strategies, enabling collective sensemaking around AI failures.
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
