Meet cybersecurity researcher Enna Basic

Large Language Models (LLMs) have emerged as powerful tools for automating various programming tasks, including security-related ones, such as detecting and fixing vulnerabilities. Despite their promising capabilities, when required to produce or modify pre-existing code, LLMs could introduce vulnerabilities unbeknown to the programmer. When analyzing code, they could miss clear vulnerabilities or signal nonexistent ones.

Enna Basic is a Cybersecurity researcher with one foot within the industry and the other within the academic world. She is one of our proud employees who is part of the Epiroc IT Security team and at the same time a PhD student in the industrial doctorate program at Örebro University.

Jonas Albertson (left) and Johan Schnürer

Epiroc and Örebro University work together under a strategic collaboration agreement with the aim to increase the quality in selected education, research and innovation enabling sustainable growth.

Read more on the agreement here: Epiroc Örebro University.

"Being an industrial doctorate at Epiroc gives you plenty of opportunities to see and understand hands-on how our machines and solutions are deployed, utilized and serviced and how technicians and machine operators interface with our highly digitalized, automated, electrified and more autonomous solutions. It really enriches the context of my research into practical situations and use cases."

Enna Basic

Enna graduated in 2023 with a Master’s degree in Computer Science with specialization in Software Engineering from Mälardalen University, Västerås, Sweden.

Enna has just submitted her first academic paper for publication, and it is now under peer review.

What have you, Enna, covered in your first academic paper?

“In this Systematic Literature Review (SLR), my aim was to investigate both the security benefits and potential drawbacks of using LLMs for a variety of code-related tasks. First, I focused on the types of vulnerabilities that could be introduced by LLMs, when used for producing code. Then I analyzed the capabilities of LLMs to detect and fix vulnerabilities, in any given code, and how the prompting strategy of choice impacts their performance in these two tasks. Finally, I provide an in-depth analysis on how data poisoning attacks on LLMs can impact performance in the aforementioned tasks.

I also want to highlight that this paper is co-authored together with my academic supervisor Alberto Giaretta, PhD in Computer Science and Deputy Head of Machine Perception and Interaction (MPI) Lab Center for Applied Autonomous Sensor Systems (AASS), Örebro University.

I am very happy to have a very supportive manager at Epiroc and a great academic supervisor at Örebro University. Professionally, I am living my dream.

My ambition for the next phases of my research is to utilize different code repositories at Epiroc while comparing and analyzing the more traditional way of coding versus the more recent practices by utilizing LLMs. What are actually the pros and cons?”

Link to the article:

“Large Language Models and Code Security: A Systematic Literature Review”

Click here to join us!

Careers