Matter
ArticleMultigenerational Crumpling of 2D Materials for Anticounterfeiting Patterns with Deep Learning Authentication
Progress and Potential
Physical unclonable function (PUF) is a cornerstone of anticounterfeiting, yet conventional PUF key-based tags encounter several bottlenecks, such as complicated manufacturing, specialized and tedious readout, long authentication time, and insufficient environmental stability. Here, we utilize two-dimensional materials (2DMs) to construct multigenerational microstructures as PUF patterns. By implementing two in situ treatments during sequential substrate contractions, multigenerational 2DM PUF patterns are produced in a transfer-free and scalable fashion. A deep learning (DL)-facilitated authentication software is further developed on the basis of the “classification and validation” mechanism, shortening the authentication time significantly. The synergy between 2DM tags and DL authentication software enables a DeepKey anticounterfeiting technology with superior encoding capacity and fast authentication, which can be integrated with QR codes to provide two-layer information security.