Breakable Machine: A K-12 Classroom Game for Transformative AI Literacy Through Spoofing and eXplainable AI (XAI)

2025-08-19

AI Summary

Current K–12 AI education (ages 10–15) overemphasizes model construction while neglecting critical AI literacy. Method: This study introduces an adversarial-game-based, deconstructive pedagogy wherein students manipulate image inputs to induce high-confidence misclassifications in classifiers and use explainable AI (XAI) techniques—particularly feature attribution visualizations—to intuitively grasp AI fragility, bias, and socio-technical implications. Model failures are reframed as collaborative inquiry opportunities, integrated with classroom leaderboards and cooperative “AI cracking” experiments. Contribution/Results: The approach reorients AI literacy toward critical thinking, data agency, and ethical awareness. All games and source code are open-sourced. Empirical evaluation demonstrates a significant cognitive shift—from “building AI” to “deconstructing and interrogating AI”—validating its efficacy in fostering critical AI literacy among young learners.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Adversarial Learning & Robustness
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

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.

Problem

• Teaching AI literacy through adversarial play and spoofing
• Exposing AI model brittleness and bias via hands-on experimentation
• Using XAI visualization to reveal model decision-making processes

Innovation

• XAI-based classroom game for AI literacy
• Spoofing image classifiers through adversarial play
• Visualizing feature saliency for model interrogation