Change search
Link to record
Permanent link

Direct link
BETA
Publications (7 of 7) Show all publications
Alberti, M., Pondenkandath, V., Würsch, M., Bouillon, M., Seuret, M., Ingold, R. & Liwicki, M. (2019). Are You Tampering with My Data?. In: Laura Leal-Taixé & Stefan Roth (Ed.), Computer Vision – ECCV 2018 Workshops: Proceedings, Part II. Paper presented at 15th European Conference on Computer Vision (ECCV), September 8-14, Munich, Germany (pp. 296-312). Springer
Open this publication in new window or tab >>Are You Tampering with My Data?
Show others...
2019 (English)In: Computer Vision – ECCV 2018 Workshops: Proceedings, Part II / [ed] Laura Leal-Taixé & Stefan Roth, Springer, 2019, p. 296-312Conference paper, Published paper (Refereed)
Abstract [en]

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during training which can be exploited at test time to force a neural network to exhibit abnormal behaviour. We demonstrate on two widely used datasets (CIFAR-10 and SVHN) that a universal modification of just one pixel per image for all the images of a class in the training set is enough to corrupt the training procedure of several state-of-the-art deep neural networks, causing the networks to misclassify any images to which the modification is applied. Our aim is to bring to the attention of the machine learning community, the possibility that even learning-based methods that are personally trained on public datasets can be subject to attacks by a skillful adversary.

Place, publisher, year, edition, pages
Springer, 2019
Series
Lecture Notes in Computer Science ; 11130
Keywords
Adversarial attack, Machine learning, Deep neural networks, Data poisoning
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-73147 (URN)10.1007/978-3-030-11012-3_25 (DOI)2-s2.0-85061797135 (Scopus ID)978-3-030-11011-6 (ISBN)
Conference
15th European Conference on Computer Vision (ECCV), September 8-14, Munich, Germany
Available from: 2019-03-11 Created: 2019-03-11 Last updated: 2019-03-11Bibliographically approved
Maergner, P., Pondenkandath, V., Alberti, M., Liwicki, M., Riesen, K., Ingold, R. & Fischer, A. (2019). Combining graph edit distance and triplet networks for offline signature verification. Pattern Recognition Letters, 125, 527-533
Open this publication in new window or tab >>Combining graph edit distance and triplet networks for offline signature verification
Show others...
2019 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 125, p. 527-533Article in journal (Refereed) Published
Abstract [en]

Offline signature verification is a challenging pattern recognition task where a writer model is inferred using only a small number of genuine signatures. A combination of complementary writer models can make it more difficult for an attacker to deceive the verification system. In this work, we propose to combine a recent structural approach based on graph edit distance with a statistical approach based on deep triplet networks. The combination of the structural and statistical models achieve significant improvements in performance on four publicly available benchmark datasets, highlighting their complementary perspectives.

Place, publisher, year, edition, pages
Elsevier, 2019
Keywords
Offline signature verification, Graph edit distance, Metric learning, Deep convolutional neural network, Triplet network
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-75255 (URN)10.1016/j.patrec.2019.06.024 (DOI)000482374500072 ()2-s2.0-85067868377 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-08-20 (johcin)

Available from: 2019-07-08 Created: 2019-07-08 Last updated: 2019-09-13Bibliographically approved
Adewumi, O., Liwicki, F. & Liwicki, M. (2019). Conversational Systems in Machine Learning from the Point of View of the Philosophy of Science—Using Alime Chat and Related Studies. Philosophies, 4(3), Article ID 41.
Open this publication in new window or tab >>Conversational Systems in Machine Learning from the Point of View of the Philosophy of Science—Using Alime Chat and Related Studies
2019 (English)In: Philosophies, ISSN 2409-9287, Vol. 4, no 3, article id 41Article in journal (Refereed) Published
Abstract [en]

This essay discusses current research efforts in conversational systems from the philosophy of science point of view and evaluates some conversational systems research activities from the standpoint of naturalism philosophical theory. Conversational systems or chatbots have advanced over the decades and now have become mainstream applications. They are software that users can communicate with, using natural language. Particular attention is given to the Alime Chat conversational system, already in industrial use, and the related research. The competitive nature of systems in production is a result of different researchers and developers trying to produce new conversational systems that can outperform previous or state-of-the-art systems. Different factors affect the quality of the conversational systems produced, and how one system is assessed as being better than another is a function of objectivity and of the relevant experimental results. This essay examines the research practices from, among others, Longino’s view on objectivity and Popper’s stand on falsification. Furthermore, the need for qualitative and large datasets is emphasized. This is in addition to the importance of the peer-review process in scientific publishing, as a means of developing, validating, or rejecting theories, claims, or methodologies in the research community. In conclusion, open data and open scientific discussion fora should become more prominent over the mere publication-focused trend.

Place, publisher, year, edition, pages
Switzerland: MDPI, 2019
Keywords
conversational systems, chatbots, philosophy of science, objectivity, verification, falsification
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-75430 (URN)10.3390/philosophies4030041 (DOI)
Note

Validerad;2019;Nivå 1;2019-09-18 (marisr)

Available from: 2019-08-08 Created: 2019-08-08 Last updated: 2019-09-18Bibliographically approved
Alberti, M., Pondenkandath, V., Wursch, M., Ingold, R. & Liwicki, M. (2018). DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments. In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018: . Paper presented at 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, 5- August 2018, Niagara Fall, United States (pp. 423-428). IEEE, Article ID 8583798.
Open this publication in new window or tab >>DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
Show others...
2018 (English)In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, IEEE, 2018, p. 423-428, article id 8583798Conference paper, Published paper (Refereed)
Abstract [en]

We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality. Reproducing scientific results can be a frustrating experience, not only in document image analysis but in machine learning in general. Using DeepDIVA a researcher can either reproduce a given experiment or share their own experiments with others. Moreover, the framework offers a large range of functions, such as boilerplate code, keeping track of experiments, hyper-parameter optimization, and visualization of data and results. To demonstrate the effectiveness of this framework, this paper presents case studies in the area of handwritten document analysis where researchers benefit from the integrated functionality. DeepDIVA is implemented in Python and uses the deep learning framework PyTorch. It is completely open source(1), and accessible as Web Service through DIVAServices(2).

Place, publisher, year, edition, pages
IEEE, 2018
Series
International Conference on Handwriting Recognition, ISSN 2167-6445
Keywords
Framework, Open-Source, Deep Learning, Neural Networks, Reproducible Research, Machine Learning, Hyper-parameters Optimization, Python
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-73160 (URN)10.1109/ICFHR-2018.2018.00080 (DOI)000454983200071 ()2-s2.0-85052223452 (Scopus ID)978-1-5386-5875-8 (ISBN)
Conference
16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, 5- August 2018, Niagara Fall, United States
Available from: 2019-03-11 Created: 2019-03-11 Last updated: 2019-09-13Bibliographically approved
Pondenkandath, V., Alberti, M., Eichenberger, N., Ingold, R. & Liwicki, M. (2018). Identifying cross-depicted historical motifs. In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018: . Paper presented at 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, 5- August 2018, Niagara Fall, United States (pp. 333-338). IEEE, Article ID 8583783.
Open this publication in new window or tab >>Identifying cross-depicted historical motifs
Show others...
2018 (English)In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, IEEE, 2018, p. 333-338, article id 8583783Conference paper, Published paper (Refereed)
Abstract [en]

Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners.This is a common problem in handwritten historical document image analysis, for instance when the same letter or motif is depicted in several different ways. It is a simple task for humans yet conventional computer vision methods struggle to cope with it. In this paper we address this problem using state-of-the-art deep learning techniques on a dataset of historical watermarks containing images created with different methods of reproduction, such as hand tracing, rubbing, and radiography.To study the robustness of deep learning based approaches to the cross-depiction problem, we measure their performance on two different tasks: Classification and similarity rankings. For the former we achieve a classification accuracy of 96 % using deep convolutional neural networks. For the latter we have a false positive rate at 95% recall of 0.11. These results outperform state-of-the-art methods by a significant margin

Place, publisher, year, edition, pages
IEEE, 2018
Series
International Conference on Handwriting Recognition, ISSN 2167-6445
Keywords
convolutional neural network, cross-depiction, deep learning, machine learning, watermarks
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-72981 (URN)10.1109/ICFHR-2018.2018.00065 (DOI)000454983200056 ()2-s2.0-85060032898 (Scopus ID)978-1-5386-5875-8 (ISBN)
Conference
16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, 5- August 2018, Niagara Fall, United States
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-03-11Bibliographically approved
Kolsch, A., Mishra, A., Varshneya, S., Afzal, M. & Liwicki, M. (2018). Recognizing challenging handwritten annotations with fully convolutional networks. In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018: . Paper presented at 16th International Conference on Frontiers in Handwriting Recognition( ICFHR 2018), 5-8 August 2018, Niagara Falls, United States (pp. 25-31). IEEE, Article ID 8563221.
Open this publication in new window or tab >>Recognizing challenging handwritten annotations with fully convolutional networks
Show others...
2018 (English)In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, IEEE, 2018, p. 25-31, article id 8563221Conference paper, Published paper (Refereed)
Abstract [en]

This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents. The handwritten annotations can appear in form of underlines and text by using various writing instruments, e.g., the use of pencils makes the data more challenging. We train and evaluate various end-to-end semantic segmentation approaches and report the results. The task is to classify the pixels of documents into two classes: Background and handwritten annotation. The best model achieves a mean Intersection over Union (IOU) score of 95.6% on the test documents of the presented dataset. We also present a comparison of different strategies used for data augmentation and training on our presented dataset. For evaluation, we use the Layout Analysis Evaluator for the ICDAR 2017 Competition on Layout Analysis for Challenging Medieval Manuscripts.

Place, publisher, year, edition, pages
IEEE, 2018
Series
International Conference on Handwriting Recognition, ISSN 2167-6445
Keywords
Annotation Detection, Deep Learning, Segmentation
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-72980 (URN)10.1109/ICFHR-2018.2018.00014 (DOI)000454983200005 ()2-s2.0-85060050050 (Scopus ID)978-1-5386-5875-8 (ISBN)
Conference
16th International Conference on Frontiers in Handwriting Recognition( ICFHR 2018), 5-8 August 2018, Niagara Falls, United States
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-03-11Bibliographically approved
Eichenberger, N., Garz, A., Chen, K., Wei, H., Ingold, R. & Liwicki, M. (2014). DivaDesk: A Holistic Digital Workspace for Analyzing Historical Document Images. Paper presented at Conference on Natural Sciences and Technology in Manuscript Analysis'at the University of Hamburg,SFB 950, Manuskriptkulturen in Asien, Afrika und Europa, Centre for the Study of Manuscript Cultures 4–6 December 2013.. Manuscript Cultures, 7, 69-82
Open this publication in new window or tab >>DivaDesk: A Holistic Digital Workspace for Analyzing Historical Document Images
Show others...
2014 (English)In: Manuscript Cultures, ISSN 1867–9617, Vol. 7, p. 69-82Article in journal (Refereed) Published
Abstract [en]

In this article we present the concept of DIVADesk – a Virtual Research Environment (VRE) for scholarly work on historical documents inspired by the shift toward working with digital facsimiles. The contribution of this article is three-fold. First, a review of existing tools and projects shows that a holistic workspace integrating the latest outcomes of computational Document Image Analysis (DIA) research is still a desideratum that can only be achieved by intensive interdisciplinary collaboration. Second, the underlying modular architecture of the digital workspace is presented. It consists of a set of services that can be combined according to individual scholars’ requirements. Furthermore, interoperability with existing frameworks and services allows the research data to be shared with other VREs. The proposed DIVADesk addresses specific research with historical documents, as this is one of the hardest cases in computational DIA. The outcomes of this paradigmatic research can be transferred to other use cases in the humanities. The third contribution of this article is a description of already existing services and user interfaces to be integrated in DIVADesk. They are part of ongoing research at the DIVA research group at the University of Fribourg, Switzerland. The labeling tool DIVADIA, for example, provides methods for layout analysis, script analysis, and text recognition of historical documents. These methods build on the concept of incremental learning and provide users with semi-automatic labeling of document parts, such as text, images, and initials. The conception and realization of DIVADesk promises research outcomes both in computer science and in the humanities. Therefore, an interdisciplinary approach and intensive collaboration between scholars in the two research fields are of crucial importance.

Place, publisher, year, edition, pages
University of Hamburg, 2014
National Category
Computer Systems Computer Sciences
Research subject
Machine Learning
Identifiers
urn:nbn:se:ltu:diva-72209 (URN)
Conference
Conference on Natural Sciences and Technology in Manuscript Analysis'at the University of Hamburg,SFB 950, Manuskriptkulturen in Asien, Afrika und Europa, Centre for the Study of Manuscript Cultures 4–6 December 2013.
Note

Konferensartikel i tidskrift

Available from: 2018-12-17 Created: 2018-12-17 Last updated: 2019-04-23Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4029-6574

Search in DiVA

Show all publications