Dino Pjanic effectivized mobile communications

Publicerad: 2025-05-20

Title of thesis: Moving Towards Cognitive Radio Access Networks: Transforming MIMO Complexities into Opportunities Link to thesis in Lund University Research Portal Defence: Thursday, June 5th, in E:1406 at 09:15. Zoom link. Zoom ID:...

Title of thesis: Moving Towards Cognitive Radio Access Networks: Transforming MIMO Complexities into Opportunities

Link to thesis in Lund University Research Portal

Defence:  Thursday, June 5th, in E:1406 at 09:15.

Zoom link.
Zoom ID: 69658824268.

Describe your research in a popular science way

The introduction of advanced antenna systems marked a pivotal advancement, employing Multiple-Input Multiple-Output (MIMO) technology. These systems opened new avenues for understanding channel characteristics. An apt analogy for these systems is a large astronomical observatory employing an array of telescopes scattered across the globe to observe the same distant object. Each telescope collects a unique portion of the light or radio waves, influenced by its position and angle. By combining the data from all telescopes, a more detailed and multi-dimensional image is created, surpassing what a single telescope could achieve. In recent years, modern cellular networks have faced new requirements beyond traditional communication between users and the network, including integrated wireless sensing. Wireless sensing utilizes existing communication signals to perceive and interpret the surrounding environment. From a network perspective, this involves leveraging cellular infrastructure to enable sensing without the need for additional dedicated sensors. Rather than solely transmitting data, the network can analyze signals to detect object presence and movement, user positioning, and environmental changes. My thesis partly examines various aspects of wireless sensing, a field still in its early stages at the time of writing. The telecommunications industry is transitioning toward the next generation of networks, 6G, focusing on terabit-level speeds, holographic communication, and AI-driven networks. Unlike traditional communication paradigms, which rely on a reactive approach where receivers wait for signals, cognitive cellular networks will utilize predictive capabilities to anticipate traffic demands and upcoming events. This thesis leverages AI, which, unlike traditional programmed devices, is adaptive, probabilistic, and capable of learning from data to make autonomous decisions. The question of how AI can enable cognitive mobile networks by utilizing MIMO-based "telescopes" to predict user movement patterns or radio channel characteristics over both short and long time horizons is addressed in the thesis. AI technology holds transformative potential to revolutionize cellular network operations by leveraging historical data to enable intelligent, autonomous functionality with minimal human intervention.

Artistic illustration of the concept of spatial fingerprinting.

What made you want to pursue a PhD?

By nature, I constantly seek out new challenges. After 20 years of experience in the industry, I decided it was time to take the next step venturing into the unknown and stepping out of my comfort zone. It?s in these moments, when the ground feels uncertain, that I tend to grow the most as a person.

What is the most fascinating or interesting with your thesis subject?
 
How the interaction between technological challenges and recent advances in machine learning and AI offers new insights and solutions to complex problems.

Do you believe some results from your research will be applied in practice eventually? And if so, how / how?

Definitely, when I began my PhD, this research field was still largely unexplored, especially from an industrial perspective. Today, AI is regarded as essential for the future of telecommunications systems.

What are your plans?

As an industrial PhD at Ericsson in Lund, it feels natural to return and apply the skills and insights I?ve gained.

Länk till artikeln Dino Pjanic effectivized mobile communications

Syafiq Al Atiiq hardened software against attacks

Publicerad: 2025-05-05

Title of thesis: Principles and Solutions for Improved Availability and Code Vulnerability Detection Link to thesis in Lund University Research Portal Defence: Friday, May 16th, in E:1406 at 13:15. Zoom link. Zoom ID:...

Title of thesis: Principles and Solutions for Improved Availability and Code Vulnerability Detection

Link to thesis in Lund University Research Portal

Defence:  Friday, May 16th, in E:1406 at 13:15.

Zoom link.
Zoom ID: 68034306533.

Describe your research in a popular science way

My research explored the following question: how do we ensure our system remains available when facing attacks or failures?
I focus on three areas. First, I've developed protocols for Internet of Things (IoT) devices, shielding these resource-limited devices from being overwhelmed by malicious traffic and help them recover after compromise.
Second, I've investigated security vulnerabilities in 5G networks, particularly in their AI-driven mobility prediction systems. I've shown that even a small number of fake devices can significantly reduce prediction accuracy and identified strategies to make these systems more resilient.
Finally, I've explored how artificial intelligence can automatically detect vulnerabilities in software before they become security problems. My research reveals that different programming languages and vulnerability types perform variably.

What made you want to pursue a PhD?

My path to doctoral studies emerged at a professional crossroads after experiencing both the startup and corporate worlds as an employee. This transition period gave me the opportunity to reflect on what truly mattered to me professionally.

What is the most fascinating or interesting with your thesis subject?

Most of the work here is based on real-world problems, and sometimes the most intuitive solution is not always the best one. One example would be that, intuitively, the larger the AI model is, the better the performance should be. But we show that smaller models can perform better (with less inference cost), at least in the vulnerability detection problem that we explored.

Do you believe some results from your research will be applied in practice eventually? And if so, how / how?

Yes! We have a product based on the last two papers of this dissertation. There is a company called VyPr AI, tackling software vulnerability detection using (some of) our results.

Länk till artikeln Syafiq Al Atiiq hardened software against attacks

Joakim Brorsson studied the security of Trusted Third Parties

Publicerad: 2025-02-25

Title of thesis: On the Trustworthiness of Trusted Third Parties Link to thesis in Lund University Research Portal: https://portal.research.lu.se/sv/publications/on-the-trustworthiness-of-trusted-third-parties Defence: Friday, March 7th, in...

Title of thesis: On the Trustworthiness of Trusted Third Parties
Link to thesis in Lund University Research Portal:

https://portal.research.lu.se/sv/publications/on-the-trustworthiness-of-trusted-third-parties

Defence:  Friday, March 7th, in E:1406 at 09:15.

Zoom link: https://lu-se.zoom.us/j/67331586615
Zoom ID: 67331586615.

Describe your research in a popular science way
Much of the security of today?s IT-systems depend on trusting central points. For example, the secure connection your browser makes when visiting a webpage is guaranteed in part by a central party which certifies the legitimacy of web pages. If such a central party fails in its security, and there are many practical examples of such events, the consequences are large. My research is aimed at getting rid of as much trust as possible in these trusted parties.

What made you want to pursue a PhD?
After graduating with a master?s degree and beginning to work in the cybersecurity industry, I often found that existing ways of building secure systems felt inadequate. However, my knowledge was not deep enough to propose the needed improvements. A PhD was the prefect way of acquiring the needed knowledge.

Do you believe some results from your research will be applied in practice eventually? And if so, how / how?
I really hope that my final paper called Consistency-or-Die, or some follow up work to it, gets deployed in practice. The paper points out security problems in deployed large-scale systems called Key Transparency logs, which are part of the security in WhatsApp and iMessage, and proposes practical solutions. I also think that some of my research on Intel SGX is valuable in practice.

What are your plans?
I am now working at the cybersecurity company Hyker, which I co-founded before pursuing a PhD, and which has inspired part of my research. At Hyker, I can use knowledge acquired at LTH to build better cybersecurity products which eliminate trust in trusted third parties.

Photo: Erika Weiland, Apelöga AB.

Länk till artikeln Joakim Brorsson studied the security of Trusted Third Parties