Search

With the advancement of containerization technologies and the isolation mechanisms provided by the Linux kernel through features like namespaces and cgroups, a question arises whether total isolation in containers (virtual enclave) can provide an increased level of security in all use cases. In the current paper we aim to explore the idea of unifying the container's user namespace with the host system's user namespace, to validate if this approach may increase the overall security in some areas of use. Such an approach can facilitate the implementation of complex access policies with high granularity and reduce the weak points that can lead to privilege-escalation attacks. We will explore how different containerization engines can be configured to support the user namespace unification and we will see why the Singularity containerization engine is a perfect fit for our purposes. In addition, we will propose a concept architecture for an academic cluster that can natively support the enforcement of a unified user access policy among both: underlying nodes and containers running above.

The trend of storing information on servers in the cloud raises serious security concerns since the increasing number of breaches has resulted in the theft of private data from millions of users. In case of fields like finance, where data privacy is a priority, encryption techniques are analyzed to offer certainty to the customers. A solution for this problem may be searchable encryption, a concept that permits encrypting data locally, moving it to a remote server and then performing operations directly on the ciphertext without decryption. In this paper, we implement four prominent searchable encryption techniques and thoroughly evaluate their performances for various use case scenarios in finance.

Trust is related to the performance of human teams, making it a significant characteristic, which needs to be analyzed inside human-robot teams. Trust was researched for a long time in other domains like social sciences, psychology, and economics. Building trust within a team is formed through common tasks and it depends on team performance and communication. By applying an online game based tasks for human-robot teams, the effects of three communication conditions (communication without text and verbal interaction, communication with text and verbal interaction related/not related to the task) on trust are analyzed. Additionally, we found that the participants’ background is linked to the trust in the interaction with the robot. The results show that in a human-robot team the human trust will increase more over time when he/she is working with a robot that uses text and verbal interaction communication related to the task. They further suggest that human trust will decrease to a lower extent when the robot fails in doing the tasks if it uses text and verbal communication with the human.

Research related to regulatory focus theory has shown that the way in which a message is conveyed can increase the effectiveness of the message. While different research fields have used this theory, in human-robot interaction (HRI), no real attention has been given to this theory. In this paper, we investigate it in an in the wild scenario. More specifically, we are interested in how individuals react when a robot suddenly appears at their office doors. Will they interact with it or will they ignore it? We report the results from our experimental study in which the robot approaches 42 individuals. Twenty-nine of them interacted with the robot, while the others either ignored it or avoided any interaction with it. The robot displayed two types of behavior (i.e., promotion or prevention). Our results show that individuals that interacted with a robot that matched their regulatory focus type interacted with it significantly longer than individuals that did not experience regulatory fit. Other qualitative results are also reported, together with some reactions from the participants.