Cozmo is a real-life robot designed to interact with people playing games, making sounds, expressing emotions on a LCD screen and many other pre-programmable functions. We present the development and implementation of an educational platform for Cozmo mobile robot, with several features, including web server for user interface, computer vision, voice recognition, robot trajectory tracking control, among others. Functions for educational purposes were implemented, including mathematical operations, spelling, directions, and questions functions that gives more flexibility for the teachers to create their own scripts. In this system, a cloud voice recognition tool was implemented to improve the interactive system between Cozmo and the users. Also, a cloud computing vision system was used to perform object recognition using Cozmo's camera, to be applied on educational games. Other functions were created with the purpose of controlling the emotions and the motors of Cozmo to create more sophisticated scripts. To apply the functions on Cozmo robot, an interpreter algorithm was developed to translate the functions into Cozmo's programming language. To validate this work, the proposed framework was presented to several elementary school teachers (classes with students between 4 and 12). Students and teacher's impressions are reported in this text, and indicate that the proposed system can be a useful educational tool.
Today, embedded devices such as banking/transportation cards, car keys, and mobile phones use cryptographic techniques to protect personal information and communication. Such devices are increasingly becoming the targets of attacks trying to capture the underlying secret information, e.g., cryptographic keys. Attacks not targeting the cryptographic algorithm but its implementation are especially devastating and the best-known examples are so-called side-channel and fault injection attacks. Such attacks, often jointly coined as physical (implementation) attacks, are difficult to preclude and if the key (or other data) is recovered the device is useless. To mitigate such attacks, security evaluators use the same techniques as attackers and look for possible weaknesses in order to “fix” them before deployment. Unfortunately, the attackers’ resourcefulness on the one hand and usually a short amount of time the security evaluators have (and human errors factor) on the other hand, makes this not a fair race. Consequently, researchers are looking into possible ways of making security evaluations more reliable and faster. To that end, machine learning techniques showed to be a viable candidate although the challenge is far from solved. Our project aims at the development of automatic frameworks able to assess various potential side-channel and fault injection threats coming from diverse sources. Such systems will enable security evaluators, and above all companies producing chips for security applications, an option to find the potential weaknesses early and to assess the trade-off between making the product more secure versus making the product more implementation-friendly. To this end, we plan to use machine learning techniques coupled with novel techniques not explored before for side-channel and fault analysis. In addition, we will design new techniques specially tailored to improve the performance of this evaluation process. Our research fills the gap between what is known in academia on physical attacks and what is needed in the industry to prevent such attacks. In the end, once our frameworks become operational, they could be also a useful tool for mitigating other types of threats like ransomware or rootkits.
This project addresses the fundamental societal problem that encryption as a technique is available since decades, but has never been widely adopted, mostly because it is too difficult or cumbersome to use for the public at large. PGP illustrates this point well: it is difficult to set-up and use, mainly because of challenges in cryptographic key management. At the same time, the need for encryption has only been growing over the years, and has become an urgent problem with stringent requirements – for instance for electronic communication between doctors and patients – in the General Data Protection Regulation (GDPR) and with systematic mass surveillance activities of internationally operating intelligence agencies. The interdisciplinary project "Encryption for all" addresses this fundamental problem via a combination of cryptographic design and user experience design. On the cryptographic side it develops identity-based and attribute-based encryption on top of the attribute-based infrastructure provided by the existing IRMA-identity platform. Identity-based encryption (IBE) is a scientifically well-established technique, which addresses the key management problem in an elegant manner, but IBE has found limited application so far. In this project it will be developed to a practically usable level, exploiting the existing IRMA platform for identification and retrieval of private keys. Attribute-based encryption (ABE) has not reached the same level of maturity yet as IBE, and will be a topic of further research in this project, since it opens up attractive new applications: like a teacher encrypting for her students only, or a company encrypting for all employees with a certain role in the company. On the user experience design side, efforts will be focused on making these encryption techniques really usable (i.e., easy to use, effective, efficient, error resistant) for everyone (e.g., also for people with disabilities or limited digital skills). To do so, an iterative, human-centred and inclusive design approach will be adopted. On a fundamental level, scientific questions will be addressed, such as how to promote the use of security and privacy-enhancing technologies through design, and whether and how usability and accessibility affect the acceptance and use of encryption tools. Here, theories of nudging and boosting and the unified theory of technology acceptance and use (known as UTAUT) will serve as a theoretical basis. On a more applied level, standards like ISO 9241-11 on usability and ISO 9241-220 on the human-centred design process will serve as a guideline. Amongst others, interface designs will be developed and focus groups, participatory design sessions, expert reviews and usability evaluations with potential users of various ages and backgrounds will be conducted, in a user experience and observation laboratory available at HAN University of Applied Sciences. In addition to meeting usability goals, ensuring that the developed encryption techniques also meet national and international accessibility standards will be a particular point of focus. With respect to usability and accessibility, the project will build on the (limited) usability design experiences with the mobile IRMA application.
Lack of physical activity in urban contexts is an increasing health risk in The Netherlands and Brazil. Exercise applications (apps) are seen as potential ways of increasing physical activity. However, physical activity apps in app stores commonly lack a scientific base. Consequently, it remains unknown what specific content messages should contain and how messages can be personalized to the individual. Moreover, it is unknown how their effects depend on the physical urban environment in which people live and on personal characteristics and attitudes. The current project aims to get insight in how mobile personalized technology can motivate urban residents to become physically active. More specifically, we aim to gain insight into the effectiveness of elements within an exercise app (motivational feedback, goal setting, individualized messages, gaming elements (gamification) for making people more physically active, and how the effectiveness depends on characteristics of the individual and the urban setting. This results in a flexible exercise app for inactive citizens based on theories in data mining, machine learning, exercise psychology, behavioral change and gamification. The sensors on the mobile phone, together with sensors (beacons) in public spaces, combined with sociodemographic and land use information will generate a massive amount of data. The project involves analysis in two ways. First, a unique feature of our project is that we apply machine learning/data mining techniques to optimize the app specification for each individual in a dynamic and iterative research design (Sequential Multiple Assignment Randomised Trial (SMART)), by testing the effectiveness of specific messages given personal and urban characteristics. Second, the implementation of the app in Sao Paolo and Amsterdam will provide us with (big) data on use of functionalities, physical activity, motivation etc. allowing us to investigate in detail the effects of personalized technology on lifestyle in different geographical and cultural contexts.
