Recovering information from pixelized credentials
| dc.contributor.author | Garske, Viktor | |
| dc.contributor.author | Noack, Andreas | |
| dc.contributor.editor | Christian Wressnegger, Delphine Reinhardt | |
| dc.date.accessioned | 2023-01-24T11:17:53Z | |
| dc.date.available | 2023-01-24T11:17:53Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Pixelation is a common technique to redact sensitive information like credentials in images. In this paper, we propose a system that is able to recover information from pixelized text. Our contribution consists of a neural network as well as a generic pipeline that generates a realistic training dataset considering flexible specifications including wordlists, fonts, font sizes and letter spacings. The contributed neural network is a composition of a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN) using Long short-term memory (LSTM) and a Connectionist Temporal Classification (CTC) layer to decode sequences of characters. With our approach, we achieve a Label Error Rate (LER) under 50% when taking pixelation block sizes of up to 8 × 8 pixels on a 22pt font into account. Thereby, our results indicate that pixelation of sensitive data does not satisfy common privacy standards. | en |
| dc.identifier.doi | 10.18420/sicherheit2022_08 | |
| dc.identifier.isbn | 978-3-88579-717-3 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/40150 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik, Bonn | |
| dc.relation.ispartof | GI SICHERHEIT 2022 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-323 | |
| dc.subject | Neural networks | |
| dc.subject | privacy | |
| dc.subject | machine learning | |
| dc.subject | computer vision | |
| dc.subject | password | |
| dc.subject | credentials | |
| dc.subject | pixelized | |
| dc.title | Recovering information from pixelized credentials | en |
| gi.citation.endPage | 141 | |
| gi.citation.startPage | 129 | |
| gi.conference.date | 5.-8. April 2022 | |
| gi.conference.location | Karlsruhe | |
| gi.conference.sessiontitle | Session 3 |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- B3-1.pdf
- Größe:
- 799.83 KB
- Format:
- Adobe Portable Document Format