Publications #

Here are my research publications:

2026 #

• Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture The Flag Challenges (AIWare'26)
  Ali Al-Kaswan, Maksim Plotnikov, Maxim Hájek, Roland Vízner, Arie van Deursen, Maliheh Izadi

• AST-PAC: AST-guided Membership Inference for Code (FSE-IVR'26) Roham Koohestani, Ali Al-Kaswan, Jonathan Katzy, Maliheh Izadi

• Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs (MSR'26) Ali Al-Kaswan, Claudio Spiess, Prem Devanbu, Arie van Deursen, Maliheh Izadi

2025 #

• Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks (FSE'25)
  Ali Al-Kaswan, Sebastian Deatc, Begüm Koç, Arie van Deursen, Maliheh Izadi

2024 #

• Traces of Memorisation in Large Language Models for Code (ICSE'24)
  Ali Al-Kaswan, Maliheh Izadi, Arie van Deursen

• Towards Safe, Secure, and Usable LLMs4Code (ICSE DocSym'24)
  Ali Al-Kaswan

2023 #

• The (ab)use of Open Source Code to Train Large Language Models (NLBSE'23)
  Ali Al-Kaswan, Maliheh Izadi, Arie van Deursen

• STACC: Code Comment Classification using SentenceTransformers (NLBSE'23)
  Ali Al-Kaswan, Maliheh Izadi, Arie van Deursen

• Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge (2023)
  Ali Al-Kaswan, Maliheh Izadi, Arie van Deursen

• Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries (SANER'23)
  Ali Al-Kaswan, Toufique Ahmed, Maliheh Izadi, Anand Ashok Sawant, Premkumar Devanbu, Arie van Deursen