报告时间：2019年12月23日（星期一）下午14：00
报告地点：浙江大学紫金港校区蒙民伟楼402室
报告题目：Embedding Information in Text Documents using Glyph Perturbation
主讲人：Chang Xiao（Columbia University）
主持人：邵天甲研究员

Abstract: We introduce FontCode, an information embedding technique for text documents. Provided a text document with specific fonts, our method embeds user-specified information in the text by perturbing the glyphs of text characters while preserving the text content. We devise an algorithm to choose unobtrusive yet machine-recognizable glyph perturbations, leveraging a recently developed generative model that alters the glyphs of each character continuously on a font manifold. We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whose appearance is minimally perturbed from the original document. We also present a glyph recognition method that recovers the embedded information from an encoded document stored as a vector graphic or pixel image, or even on a printed paper. In addition, we introduce a new error-correction coding scheme that rectifies a certain number of recognition errors. Lastly, we demonstrate that our technique enables a wide array of applications, using it as a text document metadata holder, an unobtrusive optical barcode, a cryptographic message embedding scheme, and a text document signature.

Bio: Chang Xiao is a fourth-year PhD student at Columbia University, advised by Prof. Changxi Zheng. His research interests focus on human computer interaction and machine learning. He published multiple papers in top conference including SIGGRAPH, NeurIPS and ICLR. Previously, he obtained his bachelor degree in the College of Computer Science (Chu Kochen Honors College) of Zhejiang University in 2016. He received the Snap Research Fellowship and CKGSB Doctoral Fellowship in 2018.