AutoStegaFont: Synthesizing Vector Fonts for Hiding Information in Documents
Authors: Xi Yang, Jie Zhang, Han Fang, Chang Liu, Zehua Ma, Weiming Zhang, Nenghai Yu
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate the superior performance of our scheme in automatically synthesizing vector fonts for hiding information in documents, with robustness to distortions caused by low-resolution screenshots, printing, and photography. |
| Researcher Affiliation | Academia | Xi Yang1, Jie Zhang1,2, Han Fang*3, Chang Liu1, Zehua Ma1, Weiming Zhang*1, Nenghai Yu1 1University of Science and Technology of China 2University of Waterloo 3National University of Singapore |
| Pseudocode | Yes | Algorithm 1: Optimization-based encoding. |
| Open Source Code | No | The paper does not include an unambiguous statement that the authors are releasing the source code for their own method, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | We select Times New Roman and Helvetica as representatives of serif and sans-serif English fonts, respectively. Besides, to verify the generalizability of our framework in different languages, we also conduct experiments on Song, which is the most commonly used Chinese font. We use the open source font editor Font Forge1 to obtain rendered glyph images and corresponding SVG commands. 1https://fontforge.org/ |
| Dataset Splits | No | The paper does not specify exact split percentages or absolute sample counts for training, validation, or test sets, nor does it reference predefined splits with citations for dataset partitioning. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run its experiments, such as GPU or CPU models, or memory specifications. |
| Software Dependencies | No | The paper mentions using 'Adam' as an optimizer and 'Font Forge' as an open-source font editor, but it does not provide specific version numbers for these or any other key software dependencies or libraries. |
| Experiment Setup | Yes | For the weight factors in the first stage, we set λvq = 5, λpercep = 0.01, λm = λA = 1. In the second stage, we set λimg = 1 and λmsg = 10−5. The number of iterations k is set to 200. |