Thesis in Progress

19 Entries found


TCP performance in wireless multi-hop networks (WMNs) is hard to achieve due to losses on the wireless channel, interferences and limited resources at individual nodes. Recent research has proposed a simple neural network (NN) structure with one input layer, two hidden layers, and one output layer that efficiently applies congestion control and that results in significant performance improvements compared to conventional TCP variants [1].

Further, NeuroEvolution of Augmenting Topologies (NEAT) is a method based on evolutionary algorithms that can outperform fixed-topology NNs in reinforcement learning tasks. We expect that NEAT may improve the performance of manually crafted NNs like iTCP even further.

This project addresses the problem of energy-efficient data dissemination from a source node to all other nodes in a wireless multi-hop network. Mahdi Mousavi et al. from the Communications Engineering Lab at TU Darmstadt have devised a decentralized algorithm towards this goal that is based on game theory [1]. While simulation results have shown that this mechanism significantly outperforms other conventional flooding mechanisms, its practical applicability still remains unexplored.

Every day new cyber security vulnerabilities are discovered and reported, which indicate weak security standards adapted by websites. The main aim of a hacker is to steal sensitive information by exploiting these vulnerabilities. The information and data compromised can be very costly and damaging for an organization. Hence, due to ever evolving tactics of the hackers and the changing cyber threat landscape, it is very important for an organization to be aware of the security vulnerabilities.

Until now, most of the work which is done allows to discover the vulnerabilities in web applications and anticipate the vulnerabilities exploits. Different techniques are used in this regard, including machine learning, evaluating inter-module relationships, and application of data analytics. All of these approaches have a common goal, which is to discover existing and new vulnerabilities and predict them for future. Some solutions consider evaluating the application code by performing static or dynamic analysis and finding vulnerabilities. However, a very critical question in this whole scenario arises, as to what we can do after a vulnerability is discovered? How to find similar vulnerabilities in the system and share this information with others for proactive resolution of the vulnerabilities? In this regard, data analysis of security vulnerabilities can provide a wealth of information. It can provide efficient vulnerability assessment by analyzing the existing vulnerability data.

IoT Web Security

Master Thesis

Fitbit Security

Master Thesis

Knowledge of global network state is crucial for several innovative network optimization techniques. Essentially, incorporating knowledge about the overall network state into locally made decisions at decentralized nodes might improve the overall network performance. A node might for instance perform transitions between network mechanisms that are optimized for certain network conditions. However, an individual node's scope of the network is limited in practice since it is able to overhear the wireless channel only locally, and explicit notification about global network state would result in large overhead. Therefore, we seek to extend a node's view into the network by means of machine learning techniques.

Prof. Dr.-Ing. Matthias Hollick

Technische Universität Darmstadt
Department of Computer Science
Secure Mobile Networking Lab 

Mornewegstr. 32 (S4/14)
64293 Darmstadt, Germany

Phone: +49 6151 16-25472
Fax: +49 6151 16-25471

A A A | Drucken Drucken | Impressum Impressum | Sitemap Sitemap | Suche Suche | Kontakt Kontakt | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang