Electronic Communications of the EASST (European Association of Software Science and Technology)
Not a member yet
887 research outputs found
Sort by
Property Inference-based Federated Learning Groups for Collaborative Network Anomaly Detection
Full text linkWhile the use of anomaly detection in network security has a long research history, it is rarely used in practice. Besides privacy concerns when applied in cross-network settings, and a more difficult attack interpretation, the major drawback consists of the high number of false alarms. One reason is the heterogeneity of sources the model is trained on. In this paper, we propose a network anomaly detection extension that counteracts the heterogeneity of participants by dividing them into learning groups during central or federated training. The learning groups finally contain similar behaving clients, e.g., light bulbs, or PCs of the same department. Similar behavior is extracted by hierarchically clustering the predictions of all individual client models similar to a passive property inference attack. Our preliminary results based on infiltration attacks of the IDS2017 dataset show that the method increases the accuracy and F1 score up to 4.4% and 2.5%, respectively
Improvements to the Secure Construction and Utilization of Greedy Embeddings in Friend-to-Friend Overlays
Full text linkRouting based on greedy network embeddings enables efficient and privacy-preserving routing in overlays where connectivity is restricted to mutually trusted nodes. In previous works, we proposed security enhancements to the embedding and routing procedures to protect against denial-of-service attacks by malicious overlay participants. In this work, we propose an improved timeout scheme to reduce the stabilization overhead of secure tree maintenance in response to node failures and malicious behavior. Furthermore, we present an attack-resistant packet replication scheme that leverages alternative paths discovered during routing
FlowEmu: An Open-Source Flow-Based Network Emulator
Full text linkWhen analyzing the impact of a communication system on the Quality of Experience (QoE) of an interactive application, simulation and mathematical modeling typically require reimplementation or modeling of the application under test and only provide insights in terms of selected Key Performance Indicators (KPIs), which raises the need for network emulation. In this demo, we present FlowEmu, an open-source flow-based network emulator that allows the user to manipulate the underlying model and analyze various statistics in real-time via an easy-to-use Graphical User Interface (GUI), by using interactive game streaming as an example application
Firewall-as-a-Service for Campus Networks Based on P4-SFC
Full text linkTaking care of security is a crucial task for every operator of a campus network. One of the most fundamental security-related network functions that can be found in most networks for this purpose are stateful firewalls. However, deploying firewalls in large campus networks, e.g., at a university, can be challenging. Hardware appliances that can cope with today's high data rates at the border of a campus network are not cost-effective enough for most deployments. Shifting the responsibility to run firewalls to single departments at a university is not feasible because the expertise to manage these devices is not available there. For this reason, we propose a cloud-like infrastructure based on service function chaining (SFC) and network function virtualization (NFV) that allows users to deploy network functions like firewalls at a central place while hiding most technical details from the users
An Application Layer Protocol to Support Cooperative Navigation of Multiple UAVs Systems
Full text linkApplications involving multiple UAVs have gained increasing relevance in recent years, due to the benefits that cooperative systems tend to provide to their applications. In addition to performing several simultaneous tasks, the time spent to perform a certain task is reduced. In this article, an architecture for sharing navigation information is demonstrated to support applications composed of systems with multiple UAVs
Demo: Using LoRa Communications and Epidemic Routing in Disaster Rescue Operations
Full text linkA casualty of disasters is the communication infrastructure. Rescuers, in the aftermath of the disaster, require solutions to maintain communications in order to communicate critical information gathered by them. Despite the numerous solutions proposed, a drawback is the communication range. In this work, we propose a communication system based on LoRa, a long-range, low-power communication technology. We use the commercially available, off-the-shelf LoRa based PyCom LoPy4 platform with opportunistic networking to demonstrate the viability of using LoRa for post-disaster recovery operations
ReForm: A Tool for Rapid Requirements Formalization
Full text linkFormal methods practices can sometimes be challenging to adopt in industrial environments. On the other hand, the need for formalization and verification in the design of complex systems is now more evident than ever. To the end of easing integration of formal methods in industrial model based system engineering workflows, UTRC Ireland has developed a tool aiming to render requirements formalization as effortless as possible to the industrial engineer. The developed approach is an end-to-end solution, starting with natural language requirements as input and going all the way down to auto-generated monitors in MATLAB / Simulink. We employ natural language processing and machine learning techniques for (semi-)automatic pattern extraction from requirements, which drastically reduces the required formalization workload for both legacy and new requirements. For monitor generation, we provide our own approach which outperforms existing state-of-the-art tools by orders of magnitude in some cases
Dynamic Monitoring Area Allocation for Aerial Post-Disaster Situation Monitoring
Full text linkIn the aftermath of a disaster, information about the location of affected civilians is very important for an efficient disaster relief. A continuously operating autonomous Aerial Monitoring System with Unmanned Aerial Vehicles (UAVs) can provide an up-to-date overview of the disaster area by tracking wireless signals from carried or worn smart devices on the ground. This work highlights that dynamic allocation of monitoring areas facilitates a continuous deployment of a resilient Aerial Monitoring System with heterogeneous UAVs
Timed Automata for Mobile Ransomware Detection
Full text linkConsidering the plethora of private and sensitive information stored in smartphone and tablets, it is easy to understand the reason why attackers develop everyday more and more aggressive malicious payloads with the aim to exfiltrate our data. One of the last trend in mobile malware landascape is represented by the so-called ransomware, a threat capable to lock the user interface and to cipher the data of the mobile device under attack. In this paper we propose an approach to model an Android application in terms of timed automaton by considering system call traces i.e., performing a dynamic analysis. We obtain encouraging results in the experimental analysis we performed exploiting real-world (ransomware and legitimate) Android applications