Diqun Yan

Featured in:

Articles

Evil Operation: Breaking Speaker Recognition with PaddingBack

Aug 8, 2023 | arxiv.org | Diqun Yan |Li Dong |Kailai Shen

arXiv:2308.04179 (cs) Download a PDF of the paper titled Evil Operation: Breaking Speaker Recognition with PaddingBack, by Zhe Ye and 3 other authors Download PDF Submission history From: Diqun Yan [ view email] [v1] Tue, 8 Aug 2023 10:36:44 UTC (2,836 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Links to Code Toggle CatalyzeX Code...
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition

Aug 4, 2023 | arxiv.org | Li Dong |Jiahao Chen |Diqun Yan |Rangding Wang

Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from these images. Previous methods to prevent OCR piracy by distorting characters in text images are impractical in real-world scenarios, as pirates can capture arbitrary portions of the text images, rendering the defenses ineffective.

Try JournoFinder For Free

Search and contact over 1M+ journalist profiles, browse 100M+ articles, and unlock powerful PR tools.