Revisiting the privacy of censored credentials
Abstract
On the internet, you find numerous images like screenshots where secret parts are hidden with irreversible redaction techniques like pixelation or blurring. In this paper, we propose a system that recovers information from redacted text in raster graphics using 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 output the most probable character sequence. We furthermore show that our model operates in an automated pipeline, performs on blurred images without modification and is even able to compensate JPEG quality loss. Finally, our test results indicate that a generic neural network can be trained successfully to assist the recovery of pixelized or blurred information on screenshots or high-quality photos.
- Citation
- BibTeX
Garske, Vi. & Noack, An.,
(2022).
Revisiting the privacy of censored credentials.
In:
Demmler, D., Krupka, D. & Federrath, H.
(Hrsg.),
INFORMATIK 2022.
Gesellschaft für Informatik, Bonn.
(S. 59-70).
DOI: 10.18420/inf2022_04
@inproceedings{mci/Garske2022,
author = {Garske,Viktor AND Noack,Andreas},
title = {Revisiting the privacy of censored credentials},
booktitle = {INFORMATIK 2022},
year = {2022},
editor = {Demmler, Daniel AND Krupka, Daniel AND Federrath, Hannes} ,
pages = { 59-70 } ,
doi = { 10.18420/inf2022_04 },
publisher = {Gesellschaft für Informatik, Bonn},
address = {}
}
author = {Garske,Viktor AND Noack,Andreas},
title = {Revisiting the privacy of censored credentials},
booktitle = {INFORMATIK 2022},
year = {2022},
editor = {Demmler, Daniel AND Krupka, Daniel AND Federrath, Hannes} ,
pages = { 59-70 } ,
doi = { 10.18420/inf2022_04 },
publisher = {Gesellschaft für Informatik, Bonn},
address = {}
}
Dateien | Groesse | Format | Anzeige | |
---|---|---|---|---|
iwdf_04.pdf | 259.9Kb | View/ |
Sollte hier kein Volltext (PDF) verlinkt sein, dann kann es sein, dass dieser aus verschiedenen Gruenden (z.B. Lizenzen oder Copyright) nur in einer anderen Digital Library verfuegbar ist. Versuchen Sie in diesem Fall einen Zugriff ueber die verlinkte DOI: 10.18420/inf2022_04
Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Send Feedback
More Info
DOI: 10.18420/inf2022_04
ISBN: 978-3-88579-720-3
ISSN: 1617-5468
xmlui.MetaDataDisplay.field.date: 2022
Language: (en)