I am a PhD student at the Chair of Machine Learning and Security as part of BIFOLD and Technische Universität Berlin.
My research focuses on how real-world implementations introduce subtle and unexpected discrepancies between systems. I analyze how these differences can be exploited to undermine their integrity and how users can defend against these threats.
LLM-based Vulnerability Discovery through the Lens of Code Metrics.
48th IEEE/ACM International Conference on Software Engineering (ICSE), 2026. (to appear)
Adversarial Inputs for Linear Algebra Backends.
42nd International Conference on Machine Learning (ICML), 2025.
Dancer in the Dark: Synthesizing and Evaluating Polyglots for Blind Cross-Site Scripting.
33rd USENIX Security Symposium, 2024.
Distinguished Paper Award
SoK: Where to Fuzz? Assessing Target Selection Methods in Directed Fuzzing.
19th ACM Asia Conference on Computer and Communications Security (ASIACCS), 2024.
Cross-Language Differential Testing of JSON Parsers.
19th ACM Asia Conference on Computer and Communications Security (ASIACCS), 2024.
No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning.
32nd USENIX Security Symposium, 2023.