Lukas Pirch

LLM-based Vulnerability Discovery through the Lens of Code Metrics.
Felix Weissberg, Lukas Pirch, Erik Imgrund, Jonas Möller, Thorsten Eisenhofer and Konrad Rieck.
48th IEEE/ACM International Conference on Software Engineering (ICSE), 2026. (to appear)

Manipulating Feature Visualizations with Gradient Slingshots.
Dilyara Bareeva, Marina M.-C. Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck, Sebastian Lapuschkin and Kirill Bykov.
Advances in Neural Information Processing Systems 39 (NeurIPS), 2025. (to appear)

Adversarial Inputs for Linear Algebra Backends.
Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer and Konrad Rieck.
42nd International Conference on Machine Learning (ICML), 2025.

PDF Code

SoK: Where to Fuzz? Assessing Target Selection Methods in Directed Fuzzing.
Felix Weißberg, Jonas Möller, Tom Ganz, Erik Imgrund, Lukas Pirch, Lukas Seidel, Moritz Schloegel, Thorsten Eisenhofer and Konrad Rieck.
19th ACM Asia Conference on Computer and Communications Security (ASIACCS), 2024.

PDF Code Data

Cross-Language Differential Testing of JSON Parsers.
Jonas Möller, Felix Weißberg, Lukas Pirch, Thorsten Eisenhofer and Konrad Rieck.
19th ACM Asia Conference on Computer and Communications Security (ASIACCS), 2024.

PDF Code

Broken Promises: Measuring Confounding Effects in Learning-based Vulnerability Discovery.
Erik Imgrund, Tom Ganz, Martin Härterich, Niklas Risse, Lukas Pirch and Konrad Rieck.
16th ACM Workshop on Artificial Intelligence and Security (AISEC), 2023.

PDF

Machine Unlearning of Features and Labels.
Alexander Warnecke, Lukas Pirch, Christian Wressnegger and Konrad Rieck.
30th Network and Distributed System Security Symposium (NDSS), 2023.

PDF Code

TagVet: Vetting Malware Tags using Explainable Machine Learning.
Lukas Pirch, Alexander Warnecke, Christian Wressnegger and Konrad Rieck.
14th ACM European Workshop on Systems Security (EuroSec), 2021.

PDF