PRINTOUT · Printed Documents Authentication
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2020-06-15 → 2022-06-14
- EU contribution
- €183,473
- Participants
- 1
- Scheme
- MSCA-IF-EF-ST
Lines connect the coordinator with its partners.
Results in brief
Printed Documents Authentication
The cheap, easy access and wide use of peripheral devices such as printers and scanners have played a major role in the amount of printed information generated today. From advertisements, currencies, books, newspapers, magazines, contracts, product packaging, etc., there is always a printing technology involved. With advancements in staffless and cashless stores adoption in big cities, supermarkets and stores will make available only printed data (such as the QR-CODES) for purchases and interaction with clients, making such printing and scanning technologies crucial in a near future. Notwithstanding such advancements in the availability of printed information, the lack of regulation and forensic procedures of such kind of medium has allowed counterfeiters and other criminals to use such technology for bad purposes. For example, printed documents that are proofs in criminal investigations, such as the ones related to corruption and money laundering, can be found in a suspect's house; fake currency can be printed and distributed in a neighborhood, thus harming the local economy; domestic or international terrorist plans can be found in a facility; pedophiles can print and distribute child porn in order to avoid security agencies control over the Internet; deceivers can fake badges to have access to restricted areas, hitting up the organization and security of events. Finally, such modern technologies in printing and scanning have made counterfeiting easier and more profitable than ever, as counterfeiters can perfectly copy and print packages of fake products to resemble the original ones. Such a problem has made the International Chamber of Commerce raise an alarm of €3.7 trillion losses due to counterfeiting and piracy, with 5.4 million jobs at risk by 2022. Products counterfeiting has also a significant impact on health: according to the World Health Organization, up to half of the malaria medications could be fake. In the project PrintOut, we aim to tackle the above-mentioned problems by performing research on Computer Vision and Machine Learning solutions for printed document forensics. The project aims to tackle the following problems in research: (i) lack of cheap procedures using precise statistical models to perform robust Digital Image Forensics on printed documents; (ii) lack of comprehensive training data for machine learning models (iii) open-set (or unknown classes) classification (iv) security/adversarial attacks
Data: CORDIS, © European Union
Project objective
With the extensive range of document generation devices nowadays, the establishment of computational techniques to find manipulation, detect illegal copies and link documents to their source are useful because (i) finding manipulation can help to detect fake news and manipulated documents; (ii) exposing illegal copies can avoid frauds and copyright violation; and (iii) indicating the owner of an illegal document can provide strong arguments to the prosecution of a suspect. Different machine learning techniques have been proposed in the scientific literature to act in these problems, but many of them are limited as: (i) there is a lack of methodology, which may require different experts to solve different problems; (ii) the limited range of known elements being considered for multi-class classification problems such as source attribution, which do not consider unknown classes in a real-world testing; and (iii) they don’t consider adversarial attacks from an experienced forger. In this research project, we propose to address these problems on two fronts: resilient characterization and classification. In the characterization front, we intend to use multi-analysis approaches. Proposed by the candidate in his Ph.D. research, it is a methodology to fuse/ensemble machine learning approaches by considering several investigative scenarios, creating robust classifiers that minimize the risk of attacks. Additionally, we aim at proposing the use of open-set classifiers, which are trained to avoid misclassification of classes not included in the classifier training. We envision solutions to several printed document forensics applications with this setup: source attribution, forgery of documents and illegal copies detection. All the approaches we aim at creating in this project will be done in partnership with a document authentication company, which will provide real-world datasets and new applications.
Original text from CORDIS.
Participants
- UNIVERSITA DEGLI STUDI DI SIENA · SienaCoordinatorItaly
Links
Data: CORDIS, © European Union