Burak Hasırcıoğlu

I work as a Research Associate at The Alan Turing Institute in London, UK, focusing on the security of large language models. My research interests include differential privacy, federated learning, and coded computing.

I completed my PhD at the Information Processing and Communication Lab at Imperial College London, specializing in coded computation and secure & private distributed machine learning. I also hold an MSc in Communication Systems from EPFL in Lausanne, Switzerland and a BSc in Electrical and Electronics Engineering from METU in Ankara, Turkey.

My professional experience includes working as an Applied Scientist Intern at Amazon Web Services (AWS) in New York, US, as a design engineer at Turkish Aerospace in Ankara, Turkey, and as a research intern at ABB Corporate Research in Baden-Dättwil, Switzerland.

• Abuadbba Alsharif, Hicks Chris, Moore Kristen, Mavroudis Vasilios, Hasircioglu Burak, Goel Diksha, Jennings Piers. From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs. arxiv preprint, 2025.

• Shereen Ezzeldin, Ristea Dan, Hasircioglu Burak, McFadden Shae, Mavroudis Vasilios, Hicks Chris. One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image, arxiv preprint, 2025.

• Yilmaz Selim F., Hasircioglu Burak, Qiao Li, Gunduz Deniz. Private Collaborative Edge Inference via Over-the-Air Computation, IEEE Transactions on Machine Learning in Communications and Networking, 2025.

• Gomez-Vilardebo Jesus, Hasircioglu, Burak, and Gunduz Deniz. Generalized Multivariate Polynomial Codes for Distributed Matrix-Matrix Multiplication,  IEEE Information Theory Workshop (ITW), 2024. 

• Hasircioglu, Burak and Gunduz Deniz."Communication Efficient Private Federated Learning Using Dithering” In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. Code available on GitHub. 

• Yilmaz Selim F., Hasircioglu Burak, Gunduz Deniz, "Over-the-Air Ensemble Inference with Model Privacy", In IEEE International Symposium on Information Theory (ISIT), 2022. 

• Hasircioglu, Burak, Gomez-Vilardebo Jesus, and Gunduz Deniz. "Bivariate Polynomial Codes for Secure Distributed Matrix Multiplication". IEEE Journal on Selected Areas in Communications, 2022.

• Hasircioglu, Burak, Gomez-Vilardebo Jesus, and Gunduz Deniz. "Bivariate Polynomial Coding for Efficient Distributed Matrix Multiplication" IEEE Journal on Selected Areas in Information Theory, 2021. 

• Hasircioglu, Burak, Gomez-Vilardebo Jesus, and Gunduz Deniz. "Speeding Up Private Distributed Matrix Multiplication via Bivariate Polynomial Codes". In IEEE International Symposium on Information Theory (ISIT), 2021. 

• Malekzadeh Mohammad, Hasircioglu Burak, Mital Nitish, Katarya Kunal, Ozfatura M Emre and Gunduz Deniz."Dopamine: Differentially Private Secure Federated Learning on Medical Data." The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence(PPAI-21) 

• Hasircioglu, Burak and Gunduz Deniz."Private Wireless Federated Learning with Anonymous Over-the-Air Computation” In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

• Hasircioglu, Burak, Gomez-Vilardebo Jesus, and Gunduz Deniz."Bivariate Hermitian Polynomial Coding for Efficient Distributed Matrix Multiplication" In IEEE Global Communications Conference (Globecom) 2020. 

• Hasircioglu, Burak, Gomez-Vilardebo Jesus, and Gunduz Deniz."Bivariate Polynomial Coding For Straggler Exploitation With Heterogeneous Workers" In IEEE International Symposium on Information Theory (ISIT), 2020. 

• Hasircioglu, Burak, Yvonne-Anne Pignolet, and Thanikesavan Sivanthi. "Transparent Fault Tolerance for Real-Time Automation Systems." In Proceedings of the 1st International Workshop on Internet of People, Assistive Robots and Things, pp. 7-12. ACM, 2018.