Record link: 
http://hdl.handle.net/20.500.12708/232111
-
Title: 
Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks—RCR Report
en
Citation: 
Happe, A., & Cito, J. (2026). Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks—RCR Report. ACM Transactions on Software Engineering and Methodology, 35(11), Article 383. https://doi.org/10.1145/3800584
-
Publisher DOI: 
10.1145/3800584
-
Publication Type: 
Article - Original Research Article
en
Language: 
English
-
Authors: 
Happe, Andreas 
Cito, Jürgen 
-
Organisational Unit: 
E194-01 - Forschungsbereich Software Engineering 
-
Journal: 
ACM Transactions on Software Engineering and Methodology 
-
ISSN: 
1049-331X
-
Date (published): 
3-Nov-2026
-
Number of Pages: 
15
-
Publisher: 
ASSOC COMPUTING MACHINERY
-
Peer reviewed: 
Yes
-
Keywords: 
Large Language Models; Security; Enterprise Networks; Active Directory
en
Abstract: 
This is the Replicated Computational Results (RCR) Report for the paper “Can LLMs Hack Enterprise Networks?” The paper empirically investigates the efficacy and effectiveness of different LLMs for penetration-testing enterprise networks, i.e., Microsoft Active Directory Assumed-Breach Simulations. This RCR report describes the artifacts used in the paper, how to create an evaluation setup, and highlights the analysis scripts provided within our prototype.
en
Research Areas: 
Information Systems Engineering: 100%
-
Science Branch: 
1020 - Informatik: 90%
5020 - Wirtschaftswissenschaften: 10%
-
Appears in Collections:
Article

Show full item record

Google ScholarTM

Check