About Ali Al-Kaswan #

I ask whether we can trust AI that writes code, and try to give the field the tools to answer. I am a postdoctoral researcher at Delft University of Technology, following a PhD in its Software Engineering Research Group (thesis submitted July 2026, defence December 2026). My research covers the security and evaluation of large language models and AI agents for software engineering: what code models memorise and leak, how they behave when deployed, and how to measure what agents can reliably do.

My earlier research used pre-trained Transformers to help with reverse engineering binaries.

Studies #

I previously obtained my Master’s in Computer Science and Engineering with a specialization in Cyber Security from the Delft University of Technology. My Masters Thesis involved using Transformer models to summarise Decompiled Binaries. I have also obtained my Bachelor’s in Computer Science and Engineering from the same university, where my Bachelors Thesis involved making an inclusive game to make Datacenters more appealing to girls.

Work #

I have worked as a Junior Incident Responder at eye Security in the Hague (2021-2022). I have also been employed as a Teaching Assistant where I assisted in teaching Software Architecture, Software Engineering Methods and Computational Intelligence courses (2019-2022). Before that, I was involved in the Mentorate program for Computer Science where I helped freshmen get acquainted with university life (2018-2019).

Contact #

You can reach me on email: a.al-kaswan[at]tudelft.nl or on Twitter: @aalkaswan