REVISE
Exposing manipulated media content

Disinformation and media manipulation can strongly influence people’s perception on information and their opinion-formation. This became apparent not least during the Covid-19 pandemic and the war in Ukraine. Here, we use the term “manipulation” in a broad sense not only covering the modification of existing content but also the use of (genuine) media with malicious intent (e.g. Cybergrooming).

The REVISE research area in ATHENE is concerned with methods to detect disinformation and manipulation in different types of media, including video, image, audio or text, or a combination thereof.

Read more

ChatGPT or human author?

ATHENE scientists conduct research on automated detection capabilities.

More info

CheckThat! Lab at CLEF 2023

Lab at CLEF 2023, Task 1: Check-Worthiness in Multimodal and Multigenre Content | 1. Platz von Subtask 1A English

read more

"Wir leben im Zeitalter der Scams"

ChatGPT, Voice Cloning und Co. vereinfachen auch digitale Betrugsmaschen

read more

Publications

A Concise Analysis of Pasting Attacks and their Impact on Image Classification
Niklas Bunzel; Lukas Graner
2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2023, p.136-140

Adversarial Patch Detection and Mitigation by Detecting High Entropy Regions
Niklas Bunzel; Ashim Siwakoti; Gerrit Klause
2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2023, p.124-128

Deep­fakes, Dall-E \& Co.
Raphael Frick; Martin Steinebach; Sascha Zmudzinski
DuD: Da­ten­schutz und Datensicherheit, 2023

Detection of deepfakes using background-matching
Stephanie Blümer; Martin Steinebach; Raphael Antonius Frick; Niklas Bunzel
Electronic Imaging, 2023, Vol.35, p.381-1

Erkennung von Kindesmissbrauch in Medien
Martin Steinebach
DuD: Da­ten­schutz und Datensicherheit, 2023

Multi-Class Detection for Off The Shelf Transfer-Based Black Box Attacks
Niklas Bunzel; Dominic Böringer
Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop, 2023

Transparency in Messengers: A Metadata Analysis Based on the Example of Telegram
Karla Schäfer; Jeong-Eun Choi
Proceedings of the 34th ACM Conference on Hypertext and Social Media, 2023

A Close Look at Robust Hash Flip Positions
Martin Steinebach
Media Watermarking, Security, and Forensics 2021, 2021

Automated Image Metadata Verification
Kyra Wittorf; Martin Steinebach; Huajian Liu
Media Watermarking, Security, and Forensics 2021, 2021

Fingerprinting Blank Paper and Printed Material by Smartphones
Waldemar Berchtold; Markus Sütter; Martin Steinebach
Media Watermarking, Security, and Forensics 2021, 2021

MetaQA: Combining Expert Agents for Multi-Skill Question Answering
Haritz Puerto; Gözde Gül Sahin; Iryna Gurevych
CoRR, 2021, Vol.abs/2112.01922

Ausprägungen und Erkennung der manipulativen Verwendung von Bildern
Martin Steinebach
Betrugserkennung in der Krankenkasse. Impulsgeber für die Praxis, 2020, p.21-32

Automatisierung beim Auffinden radikaler Inhalte im Internet
Martin Steinebach; Inna Vogel; York Yannikos; Roey Regev
Extremistische Dynamiken im Social Web. Befunde zu den digitalen Katalysatoren politisch und religiös motivierter Gewalt, 2020, p.89-114

Critical traffic analysis on the tor network
Florian Platzer; Marcel Schäfer; Martin Steinebach
ARES 2020: The 15th International Conference on Availability, Reliability and Security, Virtual Event, Ireland, August 25-28, 2020, 2020, p.1-77

Fake News Detection by Image Montage Recognition
Martin Steinebach; Huajian Liu; Karol Gotkowski
Journal of Cyber Security and Mobility, 2020, Vol.9, p.175-202

Non-blind steganalysis
Niklas Bunzel; Martin Steinebach; Huajian Liu
ARES 2020: The 15th International Conference on Availability, Reliability and Security, Virtual Event, Ireland, August 25-28, 2020, 2020, p.1-71

Fake News Detection by Image Montage Recognition
Martin Steinebach; Karol Gotkowski; Huajian Liu
Proceedings of the 14th International Conference on Availability, Reliability and Security, ARES 2019, Canterbury, UK, August 26-29, 2019, 2019, p.1-55

Fake News Detection with the New German Dataset "GermanFakeNC"
Inna Vogel; Peter Jiang
Digital Libraries for Open Knowledge - 23rd International Conference on Theory and Practice of Digital Libraries, TPDL 2019, Oslo, Norway, September 9-12, 2019, Proceedings, 2019, p.288-295

Unary and Binary Classification Approaches and their Implications for Authorship Verification
Oren Halvani; Christian Winter; Lukas Graner
CoRR, 2019, Vol.abs/1901.00399

Other thematically appropriate publications:

Fraunhofer SIT@SMM4H’22: Learning to Predict Stances and Premises in Tweets related to COVID-19 Health Orders Using Generative Models
Frick, R., & Steinebach, M. (2022, October)
In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task (pp. 111-113)

Ausprägungen von Uploadfiltern
Steinebach, M. (2022)
Selbstbestimmung, Privatheit und Da­ten­schutz (pp. 409-428). Springer Vieweg, Wiesbaden

Image montage detection based on image segmentation and robust hashing techniques
Steinebach, M., Berwanger, T., & Liu, H. (2022)
International Symposium on Electronic Imaging: Media Watermarking, Security, and Forensics 202

NoiseSeg: An image splicing localization fusion CNN with noise extraction and error level analysis branches
Gotkowski, K., Liu, H., & Steinebach, M. (2022)
International Symposium on Electronic Imaging: Media Watermarking, Security, and Forensics 2022

Maschinelles Lernen im Jugendschutz
Steinebach, M. (2022)
Mediendiskurs, Ausgabe 100

Detecting Deep­fakes with Haralicks Texture Properties
Frick, R. A., Zmudzinski, S., & Steinebach, M. (2021)
International Symposium on Electronic Imaging Science and Technology (IS&T) 2021

Automated Image Metadata Verification
Wittorf, K., Steinebach, M., & Liu, H. (2021)
Electronic Imaging, 2021(4), 274-1

Technische Herausforderungen bei der Umsetzung von Uploadfiltern
Steinebach, M. (2021)
INFORMATIK 2021

Cover-aware Steganalysis
Bunzel, N., Steinebach, M., & Liu, H. (2021)
Journal of Cyber Security and Mobility, 1-26

Automatisierte Erkennung von Desinformationen
Halvani, O., Heereman von Zuydtwyck, W., Herfert, M., Kreutzer, M., Liu, H., Simo Fhom, H.-C., Steinebach, M., Vogel, I., Wolf, R., Yannikos, Y., & Zmudzinski, S. (2020)

Checking the Integrity of Images with Signed Thumbnail Images
Steinebach, M., Jörg, S., & Liu, H. (2020)
Electronic Imaging, 2020(4), 118-1

Detecting “DeepFakes” in H. 264 Video Data Using Compression Ghost Artifacts
Frick, R. A., Zmudzinski, S., & Steinebach, M. (2020)
Electronic Imaging, 2020(4), 116-1

Fake news detection by image montage recognition
Steinebach, M., Gotkowski, K., & Liu, H. (2019, August)
Proceedings of the 14th International Conference on Availability, Reliability and Security (pp. 1-9)

Verwendung computergenerierter Kinderpornografie zu Ermittlungszwecken im Darknet
Wittmer, S., & Steinebach, M. (2019)
INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik–Informatik für Gesellschaft

Unter­stütz­ung bei Bildsichtungen durch Deep Learning
Mayer, F., & Steinebach, M. (2018)
Fachtagung Polizei-Informatik 2018

Forbild: Efficient robust image hashing
Steinebach, M., Liu, H., & Yannikos, Y. (2012, February)
In Media Watermarking, Security, and Forensics 2012 (Vol. 8303, p. 83030O). International Society for Optics and Photonics