Newest papers

AI Security Literacy: Ecosystem-based Competency Framework and K-12 Learning Platform

Eric Yocam, Varghese Mathew Vaidyan, Paris Kalathas · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28859 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

A adoção da inteligência artificial nas escolas K-12 ultrapassou a orientação para alunos, professores e administradores. Os quadros existentes de alfabetização de IA enfatizam a compreensão e o uso; os quadros de cibersegurança antecedem ameaças específicas de IA, e nem definem a alfabetização de segurança de IA como um domínio de competência em seu próprio direito. Propomos um quadro de alfabetização de segurança de IA (AISL) de seis dimensões que abrangem o ecossistema escolar, sustentam suas dimensões técnicas em referências públicas de segurança de IA e uma avaliação adversária multi-semental reproduzível, e sustentam suas dimensões de atitude em micro-dados de pesquisa representativos a nível nacional de professores e adultos dos EUA. Apenas 34.5% dos professores relatam uma política

Machine translation (Meta M2M100); the English original follows.

Abstract

Adoption of artificial intelligence in K-12 schools has outpaced guidance for students, teachers, and administrators. Existing AI-literacy frameworks emphasize understanding and use; cybersecurity frameworks predate AI-specific threats, and neither defines AI security literacy as a competency domain in its own right. We propose an AI Security Literacy (AISL) framework of six dimensions spanning the school ecosystem, ground its technical dimensions in public AI-safety benchmarks and a reproducible multi-seed adversarial evaluation, and ground its attitudinal dimensions in nationally representative survey micro-data from U.S. teachers and adults. Only 34.5% of teachers report a school AI policy, and teachers see their own AI use as easing their work but students' use as complicating it; on the technical side, a reported robustness figure depends as much on the attack and the particular trained model as on the system evaluated. NeuralFortify, a browser-based K-12 platform built on real AI models, is presented as an illustrative operationalization.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Adversarial system, Robustness (evolution), Computer science, Literacy, Domain (mathematical analysis), Work (physics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange