Fake News Detection by Image Montage Recognition





Fake news,, montage, collage, image, feature matching


Fake news have been a problem for multiple years now and in addition to this “fake images” that accompany them are becoming increasingly a problem too. The aim of such fake images is to back up the fake message itself and make it appear authentic. For this purpose, more and more images such as photo-montages are used, which have been spliced from several images. This can be used to defame people by putting them in unfavorable situations or the other way around as propaganda by making them appear more important. In addition, montages may have been altered with noise and other manipulations to make an automatic recognition more difficult. In order to take action against such montages and still detect them automated, a concept based on feature detection is developed. Furthermore, an indexing of the features is carried out by means of a nearest neighbor algorithm in order to be able to quickly compare a high number of images. Afterwards, images suspected to be a montage are reviewed by a verifier. This concept is implemented and evaluated with two feature detectors. Even montages that have been manipulated with different methods are identified as such in an average of 100 milliseconds with a probability of mostly over 90%.


Download data is not yet available.

Author Biographies

Martin Steinebach, Fraunhofer SIT, Darmstadt, Germany

Martin Steinebach is the manager of the Media Security and IT Forensics division at Fraunhofer SIT. From 2003 to 2007 he was the manager of the Media Security in IT division at Fraunhofer IPSI. He studied computer science at the Technical University of Darmstadt and finished his diploma thesis on copyright protection for digital audio in 1999. In 2003 he received his PhD at the Technical University of Darmstadt for this work on digital audio watermarking. In 2016 he became honorary professor at the TU Darmstadt. He gives lectures on Multimedia Security as well as Civil Security. He is Principle Investigator at ATHENE and represents IT Forensics and AI Security. Before he was Principle Investigator at CASED with the topics Multimedia Security and IT Forensics. In 2012 his work on robust image hashing for detection of child pornography reached the second rank Deutscher IT Sicherheitspreis, an award funded by Host Görtz.

Huajian Liu, Fraunhofer SIT, Darmstadt, Germany

Huajian Liu received his B.S. and M.S. degrees in electronic engineering from Dalian University of Technology, China, in 1999 and 2002, respectively, and his Ph.D. degree in computer science from Technical University Darmstadt, Germany, in 2008. He is currently a senior research scientist at Fraunhofer Institute for Secure Information Technology (SIT). His major research interests include information security, digital watermarking, robust hashing and digital forensics.

Karol Gotkowski, Fraunhofer SIT, Darmstadt, Germany

Karol Gotkowski received his B.S degree in computer science from Technical University Darmstadt, Germany, in 2019 and is pursuing his M.S degree in visual computing. He is currently a student assistant at Fraunhofer Institute for Secure Information Technology (SIT). His major research interests include splicing detection, visual question answering and neural network interpretability.


Pablo F Alcantarilla and T Solutions. Fast explicit diffusion for accelerated features in

nonlinear scale spaces. IEEE Trans. Patt. Anal. Mach. Intell, 34(7):1281–1298, 2011.

Steinebach, Gotkowski, Liu

Hunt Allcott and Matthew Gentzkow. Social media and fake news in the 2016 election.

Journal of economic perspectives, 31(2):211–36, 2017.

Martin Aum¨uller, Erik Bernhardsson, and Alexander Faithfull. Ann-benchmarks: A

benchmarking tool for approximate nearest neighbor algorithms. Information Systems,

Oleksandr Bailo, Francois Rameau, Kyungdon Joo, Jinsun Park, Oleksandr Bogdan, and

In So Kweon. Efficient adaptive non-maximal suppression algorithms for homogeneous

spatial keypoint distribution. Pattern Recognition Letters, 106:53–60, 2018.

Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. Surf: Speeded up robust features. In

European conference on computer vision, pages 404–417. Springer, 2006.

Sevinc Bayram, Husrev Taha Sencar, and Nasir Memon. A survey of copy-move forgery

detection techniques. In IEEE Western New York Image Processing Workshop, pages

–542. Citeseer, 2008.

Erik Bernhardsson. Annoy: Approximate nearest neighbors in c++/python, Dec 2018.

Gajanan K Birajdar and Vijay H Mankar. Digital image forgery detection using passive

techniques: A survey. Digital investigation, 10(3):226–245, 2013.

Matthew Brown, Richard Szeliski, and Simon Winder. Multi-image matching using

multi-scale oriented patches. In Computer Vision and Pattern Recognition, 2005. CVPR

IEEE Computer Society Conference on, volume 1, pages 510–517. IEEE, 2005.

Celebrandil. Celebrandil/cudasift, Oct 2018.

Zhaolin Cheng, Dhanya Devarajan, and Richard J Radke. Determining vision graphs for

distributed camera networks using feature digests. EURASIP Journal on Applied Signal

Processing, 2007(1):220–220, 2007.

Steffen Gauglitz, Luca Foschini, Matthew Turk, and Tobias H¨ollerer. Efficiently selecting

spatially distributed keypoints for visual tracking. In Image Processing (ICIP), 2011

th IEEE International Conference on, pages 1869–1872. IEEE, 2011.

David G Lowe. Distinctive image features from scale-invariant keypoints. International

journal of computer vision, 60(2):91–110, 2004.

Weiqi Luo, Jiwu Huang, and Guoping Qiu. Jpeg error analysis and its applications

to digital image forensics. IEEE Transactions on Information Forensics and Security,

(3):480–491, 2010.

Xia-mu Niu and Yu-hua Jiao. An overview of perceptual hashing. Acta Electronica

Sinica, 36(7):1405–1411, 2008.

Jinse Shin and Christoph Ruland. A survey of image hashing technique for data authentication

in wmsns. In 2013 IEEE 9th International Conference on Wireless and Mobile

Computing, Networking and Communications (WiMob), pages 253–258. IEEE, 2013.

Edson C Tandoc Jr, ZhengWei Lim, and Richard Ling. Defining “fake news” a typology

of scholarly definitions. Digital Journalism, 6(2):137–153, 2018.






ARES 2019 workshops