SciTePress - Affiliation Profile

Affiliation

Select a Subject
Refine Ontology Subject

Graz University of Technology, Austria

Context (please use complete words only)

Field

Sort by

99 Papers

A Vehicle Telematics Service for Driving Style Detection: Implementation and Privacy Challenges

Topics: Driver Behavior Analysis; Vehicle Telematics; Vehicular Cloud Computing; Mobility and the Internet of Vehicles; Security and Safety; Connected Services; Big Data and Vehicle Analytics; Traffic and Vehicle Data Collection and Processing; Information Systems and Technologies; Vehicle Information Systems

Authors: Christian Kaiser ¹ , Alexander Stocker ¹ , Andreas Festl ¹ , Marija Petrovic ¹ , Efi Papatheocharous ² , Anders Wallberg ² , Gonzalo Ezquerro ³ , Jordi Orbe ³ , Tom Szilagyi ⁴ and Michael Fellmann ⁴

Affiliations: ¹ Virtual Vehicle Research GmbH, Graz, Austria , ² RISE (Research Institutes of Sweden), Kista, Sweden , ³ JIG, Logroño, Spain , ⁴ University of Rostock, Rostock, Germany

Digital Object Identifier: 10.5220/0009329400290036

Proceedings of VEHITS 2020, ISBN: 978-989-758-419-0

Quick Abstract

Connected mobility is not only a future market, but also holds great innovation potential. The analysis of vehicle telematics data in the cloud enables novel data-driven services for several stakeholders, e.g. a mobile application for the driver to obtain his driving style. This inevitably leads to privacy concerns and the question why and when are users willing to share driving telematic data, which we addressed in an empirical study. The paper presents an implementation of a data-driven service based on vehicle telematics data and discusses how privacy issues can be tackled. For the data-driven service, the most interesting steps along the vehicle data value chain are described in detail, firstly (i) vehicle telematics data collection, secondly, (ii) the wireless data transfer to a cloud platform, and thirdly, (iii) pre-processing and data analysis to evaluate the drivers’ driving style and analyse the driving risk. Finally, (iv) a smartphone application for drivers presents driving style and driving risk data on the smartphone in an interactive way, so that the driver can work on improving both, which has a positive effect on driving and road safety.

Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net

Topics: Segmentation and Grouping; Object Detection and Localization; Medical Image Applications

Authors: Christian Payer ¹ , Darko Štern ¹ , Horst Bischof ² and Martin Urschler ³

Affiliations: ¹ Ludwig Boltzmann Institute for Clinical Forensic Imaging, Graz, Austria, Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria , ² Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria , ³ Ludwig Boltzmann Institute for Clinical Forensic Imaging, Graz, Austria, School of Computer Science, The University of Auckland, Auckland, New Zealand

Digital Object Identifier: 10.5220/0008975201240133

Proceedings of VISAPP 2020, ISBN: 978-989-758-402-2

Quick Abstract

Localization and segmentation of vertebral bodies from spine CT volumes are crucial for pathological diagnosis, surgical planning, and postoperative assessment. However, fully automatic analysis of spine CT volumes is difficult due to the anatomical variation of pathologies, noise caused by screws and implants, and the large range of different field-of-views. We propose a fully automatic coarse to fine approach for vertebrae localization and segmentation based on fully convolutional CNNs. In a three-step approach, at first, a U-Net localizes the rough position of the spine. Then, the SpatialConfiguration-Net performs vertebrae localization and identification using heatmap regression. Finally, a U-Net performs binary segmentation of each identified vertebrae in a high resolution, before merging the individual predictions into the resulting multi-label vertebrae segmentation. The evaluation shows top performance of our approach, ranking first place and winning the MICCAI 2019 Large Scale Vertebrae Segmentation Challenge (VerSe 2019).

Learning Effective Sparse Sampling Strategies using Deep Active Sensing

Topics: Machine Learning Technologies for Vision; Tracking and Visual Navigation; Mobile and Egocentric Localization

Authors: Mehdi Stapleton ¹ , Dieter Schmalstieg ² , Clemens Arth ¹ and Thomas Gloor ³

Affiliations: ¹ ICG, Graz University of Technology, Inffeldgasse 16/2, 8010 Graz, Austria, AR4 GmbH, Strauchergasse 13, 8020 Graz, Austria , ² ICG, Graz University of Technology, Inffeldgasse 16/2, 8010 Graz, Austria , ³ Hilti Corporation, Feldkircherstrasse 100, 9494 Schaan, Liechtenstein

Digital Object Identifier: 10.5220/0009172608350846

Proceedings of VISAPP 2020, ISBN: 978-989-758-402-2

Quick Abstract

Registering a known model with noisy sample measurements is in general a difficult task due to the problem in finding correspondences between the samples and points on the known model. General frameworks exist, such as variants of the classical iterative closest point (ICP) method to iteratively refine correspondence estimates. However, the methods are prone to getting trapped in locally optimal configurations, which may be far from the true registration. The quality of the final registration depends strongly on the set of samples. The quality of the set of sample measurements is more noticeable when the number of samples is relatively low (≈ 20). We consider sample selection in the context of active perception, i.e. an objective-driven decision-making process, to motivate our research and the construction of our system. We design a system for learning how to select the regions of the scene to sample, and, in doing so, improve the accuracy and efficiency of the sampling process. We present a full environment for learning how best to sample a scene in order to quickly and accurately register a model with the scene. This work has broad applicability from the fields of geodesy to medical robotics, where the cost of taking a measurement is much higher than the cost of incremental changes to the pose of the equipment.

MAUI: Tele-assistance for Maintenance of Cyber-physical Systems

Topics: Human and Computer Interaction; Assistive Computer Vision; Mobile Vision

Authors: Philipp Fleck ¹ , Fernando Reyes-Aviles ¹ , Christian Pirchheim ¹ , Clemens Arth ² and Dieter Schmalstieg ¹

Affiliations: ¹ ICG, Graz University of Technology, Inffeldgasse 16/2, 8010 Graz, Austria , ² ICG, Graz University of Technology, Inffeldgasse 16/2, 8010 Graz, Austria, AR4 GmbH, Strauchergasse 13, 8020 Graz, Austria

Digital Object Identifier: 10.5220/0009093708000812

Proceedings of VISAPP 2020, ISBN: 978-989-758-402-2

Quick Abstract

In this paper, we present the maintenance assistance user interface (MAUI), a novel approach for providing tele-assistance to a worker charged with maintenance of a cyber-physical system. Such a system comprises both physical and digital interfaces, making it challenging for a worker to understand the required steps and to assess work progress. A remote expert can access the digital interfaces and provide the worker with timely information and advice in an augmented reality display. The remote expert has full control over the user interface of the worker in a manner comparable to remote desktop systems. The worker needs to perform all physical operations and retrieve physical information, such as reading physical labels or meters. Thus, worker and remote expert collaborate not only via shared audio, video or pointing, but also share control of the digital interface presented in the augmented reality space. We report results on two studies: The first study evaluates the benefits of our system against a condition with the same cyber-physical interface, but without tele-assistance. Results indicate significant benefits concerning speed, cognitive load and subjective comfort of the worker. The second study explores how interface designers use our system, leading to initial design guidelines for tele-presence interfaces like ours.

A Comparative Study of Misapplied Crypto in Android and iOS Applications

Topics: Applied Cryptography; Security and Privacy in Mobile Systems; Software Security

Author: Johannes Feichtner

Affiliation: Institute of Applied Information Processing and Communications (IAIK), Graz University of Technology, Austria, Secure Information Technology Center – Austria (A-SIT) and Austria

Digital Object Identifier: 10.5220/0007915300960108

Proceedings of SECRYPT 2019, ISBN: 978-989-758-378-0

Quick Abstract

Many applications for Android and iOS process sensitive data and, therefore, rely on cryptographic APIs natively provided by the operating system. For this to be effective, essential rules need to be obeyed, as otherwise the attainable level of security would be weakened or entirely defeated. In this paper, we inspect the differences between Android and iOS concerning the proper usage of platform-specific APIs for cryptography. For both platforms, we present concrete strategies to detect critical mistakes and introduce a new framework for Android that excels in pinpointing the origin of problematic security attributes. Applied on real-world apps with cryptography, we find that out of 775 investigated apps that vendors distribute for both Android and iOS, 604 apps for iOS (78%) and 538 apps for Android (69%) suffer from at least one security misconception.

Related Ontology Subjects/Areas/Topics (7)

Applied Cryptography	Databases and Data Security	Security and Privacy in Mobile Systems
Cryptographic Techniques and Key Management	Information and Systems Security	Software Security
Data Engineering

Learning Task-specific Activation Functions using Genetic Programming

Topics: Machine Learning Technologies for Vision; Categorization and Scene Understanding; Deep Learning for Visual Understanding

Authors: Mina Basirat and Peter Roth

Affiliation: Institute of Computer Graphics and Vision, Graz University of Technology, Graz and Austria

Digital Object Identifier: 10.5220/0007408205330540

Proceedings of VISAPP 2019, ISBN: 978-989-758-354-4

Quick Abstract

Deep Neural Networks have been shown to be beneficial for a variety of tasks, in particular allowing for end-to-end learning and reducing the requirement for manual design decisions. However, still many parameters have to be chosen manually in advance, also raising the need to optimize them. One important, but often ignored parameter is the selection of a proper activation function. In this paper, we tackle this problem by learning task-specific activation functions by using ideas from genetic programming. We propose to construct piece-wise activation functions (for the negative and the positive part) and introduce new genetic operators to combine functions in a more efficient way. The experimental results for multi-class classification demonstrate that for different tasks specific activation functions are learned, also outperforming widely used generic baselines.

Mind the Gap: Finding What Updates Have (Really) Changed in Android Applications

Topics: Security and Privacy in Mobile Systems; Software Security

Authors: Johannes Feichtner ¹ , Lukas Neugebauer ² and Dominik Ziegler ³

Affiliations: ¹ Institute of Applied Information Processing and Communications (IAIK), Graz University of Technology, Austria, Secure Information Technology Center - Austria (A-SIT) and Austria , ² Institute of Applied Information Processing and Communications (IAIK), Graz University of Technology and Austria , ³ Know-Center GmbH and Austria

Digital Object Identifier: 10.5220/0008119303060313

Proceedings of SECRYPT 2019, ISBN: 978-989-758-378-0

Quick Abstract

Android apps often receive updates that introduce new functionality or tackle problems, ranging from critical security issues to usability-related bugs. Although developers tend to briefly denote changes when releasing new versions, it remains unclear what has actually been modified in the program code. Verifying even subtle changes between two Android apps is challenging due to the widespread use of code transformations and obfuscation techniques. In this paper, we present a new framework to precisely pinpoint differences between Android apps. By pursuing a multi-level comparison strategy that targets resources and obfuscation-invariant code elements, we succeed in highlighting similarities and changes among apps. In case studies, we demonstrate the need and practical benefits of our solution and show how well it is suited to verify changelogs.

Related Ontology Subjects/Areas/Topics (3)

Information and Systems Security

Security and Privacy in Mobile Systems

Software Security

Sensing Danger: Exploiting Sensors to Build Covert Channels

Topics: Information Hiding; Vulnerability Analysis and Countermeasures; Threat Awareness; Security Awareness and Education; Security and Privacy in Cloud and Pervasive Computing

Authors: Thomas Ulz , Markus Feldbacher , Thomas Pieber and Christian Steger

Affiliation: Institute of Technical Informatics, Graz University of Technology, Graz and Austria

Digital Object Identifier: 10.5220/0007353801000113

Proceedings of ICISSP 2019, ISBN: 978-989-758-359-9

Quick Abstract

Recent incidents have shown that sensor-equipped devices can be used by adversaries to perform malicious activities, such as spying on end-users or for industrial espionage. In this paper, we present a novel attack scenario that uses unsecured embedded sensors to build covert channels that can be used to bypass security mechanisms and transfer information between isolated processes. We present covert channels that require read- and write-access for sensor registers as well as a covert channel that transfers data by just triggering sensor readings so that malicious behavior cannot be distinguished from normal sensor usage. For each presented covert channel we discuss the trade-off between data rate and the likelihood of being detected as well as potential countermeasures. The fastest covert channel we implemented achieves a data rate of 4844 bit/s while the stealthiest but slower covert channel cannot be distinguished from normal user behavior. To highlight the significance of these security issues, we used popular platforms, such as Linux and Android, to evaluate the presented covert channels. However, we do not make any assumption regarding the device’s platform, and thus we believe that the presented exploits pose a significant security risk for any sensor-equipped device.

Related Ontology Subjects/Areas/Topics (3)

Information and Systems Security

Information Assurance

Information Hiding

Towards Continuous Sensor Operation: Modelling a Secured Smart Sensor in a Sparse Network Operated by Energy Harvesting

Topics: Performance Analysis of Wireless Networks; Modeling, Algorithms, and Performance Evaluation; Wireless Sensors, Ad-Hoc and Mesh Networks

Authors: Thomas Pieber , Benjamin Mößlang , Thomas Ulz and Christian Steger

Affiliation: Institute for Technical Informatics, Graz University of Technology, Inffeldgasse 16/I, Graz and Austria

Digital Object Identifier: 10.5220/0008053000570064

Proceedings of PECCS 2019, ISBN: 978-989-758-385-8

Quick Abstract

In modern society sensors are omnipresent. They gather information about their environment in order to optimize production flows, minimize energy usage, learn about the environment, or maximize the owner’s comfort. To achieve the desired goal in already existing buildings, sensors are introduced afterwards. These sensors might not be able to connect to a sensor network because of obstacles or user policies. If this happens, other mechanisms to create a network to gather the data need to be found. Additionally, these sensors should last for a long period and are therefore probably powered using energy harvesting methods. In this paper we present an approach for simulating the charging process of such sensors and connecting them to a network using mobile communication partners.

Related Ontology Subjects/Areas/Topics (6)

Modeling, Algorithms, and Performance Evaluation		Sensor, Mesh and Ad Hoc Communications and Networks		Wireless and Mobile Technologies
Performance Analysis of Wireless Networks		Telecommunications		Wireless Information Networks and Systems

SystemC Test Case Generation with the Gazebo Simulator

Topics: Wireless Systems; Multiscale Simulation; Industrial Processes; Computer Simulation Techniques; Robotics, Automation and Mechatronics

Authors: Thomas W. Pieber , Thomas Ulz and Christian Steger

Affiliation: Graz University of Technology, Austria

Digital Object Identifier: 10.5220/0006404800650072

Proceedings of SIMULTECH 2017, ISBN: 978-989-758-265-3

Quick Abstract

The current approach of hardware simulators are testbeds that supply the Device under Test (DUT) with inputs. These sequences of inputs are the result of engineers reverse engineering the use cases extracting the inputs from them and adding some extreme cases. This paper describes an approach where the input sequences are generated directly from the use case itself. The use case is therefore simulated in an environmental simulator such as Gazebo. This generates the stimuli for the DUT. To facilitate the compatibility between the different simulation environments we present an easy-to-use and easy-to-implement communication strategy.

Related Ontology Subjects/Areas/Topics (11)

Application Domains	Computer Simulation Techniques	Simulation and Modeling
Biomedical Engineering	Industrial Processes	Simulation Tools and Platforms
Biomedical Instruments and Devices	Multiscale Simulation	Wireless Systems
Complex Systems Modeling and Simulation	Robotics, Automation and Mechatronics

Context (please use complete words only)

Field

Sort by

Topic(s):

Filter listed results, by

Publication date

From:

To:

Author

Locate Author in list below

Data pager
Data pager
1 2 3 4 5 6 7 8 9 10 ... Page 1 of 20, items 1 to 10 of 192.

Add Author(s) to filter:

Andreas Holzinger (15)

Klaus Lenz (11)

Christian Steger (8)

Bernd Zwattendorfer (7)

Horst Bischof (7)

Christian Kreiner (6)

Bernhard Peischl (5)

Dieter Schmalstieg (5)

Alexander Oprisnik (5)

Clemens Arth (4)

Conference

Locate Conference in list below

Data pager
Data pager
1 2 3 Page 1 of 3, items 1 to 10 of 29.

Add Conference(s) to filter:

WEBIST(18)

VISAPP(16)

SECRYPT(12)

ICE-B(11)

ICINCO(5)

PECCS(4)

DCNET(4)

IVAPP(3)

BMSD(3)

MODELSWARD(2)

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject: