Teenagers' Ability to Detect Synthetic Media
Aaliya Nagori
BSides Seattle 2026 · Day 2 · Track 1
In a standout presentation from a high school senior, Aaliyah shared original research on how well teenagers can detect AI-generated synthetic videos — a question that had not been studied before her work. Using OpenAI's Sora platform to generate synthetic videos and the Pexels stock video library for authentic footage, Aaliyah surveyed 32 participants across four content categories (people, nature, animals, objects) and found that teenagers detected synthetic media with 66% accuracy while consistently underestimating their own confidence.
AI review
A surprisingly rigorous piece of original research from a high school senior that fills a genuine gap in synthetic media detection literature. The study methodology — 32 participants, Sora-generated vs. Pexels stock videos across four categories, Pearson correlation analysis — is sound for a first study. The 66% accuracy rate, reversed Dunning-Kruger pattern (87.5% underestimate confidence), and category-dependent detection (people vs. animals) are legitimate findings. This is not deep technical security research, but it is competent social science applied to a security-relevant problem.