The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Agentic Generative AI for Automation of Cyber Security Attack Chains in Tactical MANETs
Abstract
Automating cyberattack simulations is useful for evaluating the cyber resilience of mission-critical infrastructures, such as Tactical Mobile Ad-Hoc Networks (MANETs). Traditional red teaming tools lack adaptability, integration, and scalability, which limits their applicability in dynamic military environments. This paper presents an agentic generative AI system combining Cybersecurity Knowledge Graphs (CSKGs) and Large Language Model (LLM) agents. This system autonomously generates and executes context-aware cyberattack chains. The system analyzes Cyber Threat Intelligence (CTI) data, attack tool documentation, and telemetry data to plan and orchestrate multi-stage attacks using tools such as Metasploit and Sliver within an emulated environment. This approach aligns with the Software-defined Defence (SDD) paradigm by enabling software-driven, mission-adaptive simulation of Advanced Persistent Threats (APTs). We evaluate the agent system in a controlled emulated scenario, demonstrating semi-automation from semantic threat representation to system-level exploitation involving human operators.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“cooperative threat-detection agents reach over 90% classification accuracy on multi-attack IoT benchmarks [23,92]”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [92]
Citations
Cites
Design and evaluation of an Autonomous Cyber Defence agent using DRL and an augmented LLM
Loevenich, J. F., Adler, E., Hürten, T., & Lopes, R. R. F. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111162 · Cited by 57
Self-citationDesign of an Autonomous Cyber Defence Agent using Hybrid AI models
Loevenich, J. F., Adler, E., Mercier, R., Velazquez, A., & Lopes, R. R. F. (2024) · International Conference on Military Communications and Information Systems (ICMCIS) · doi:10.1109/icmcis61231.2024.10540988 · Cited by 42
Self-citationLoevenich, J. F., Adler, E., Hürten, T., Spelter, F., Roncevic, D., & Lopes, R. R. F. (2025) · International Conference on Military Communications and Information Systems (ICMCIS) · doi:10.1109/icmcis64378.2025.11047951 · Cited by 13
Self-citationA Hybrid Model for Network Condition Forecasting to Improve QoS in Tactical MANETs
Loevenich, J. F., Hürten, T., Spelter, F., Braun, J., Adler, E., Moxon, L., & Lopes, R. R. F. (2025) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms57970.2025.11073679 · Cited by 5
Self-citationOn the Challenges to Adapt to Ever-Changing Network Conditions in Tactical MANETs
Loevenich, J. F., & Lopes, R. R. F. (2025) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms57970.2025.11073706 · Cited by 4
Self-citation
Research works printed but not linked: 6
- Dey, 2020, Automated penetration testing using machine learning, IEEE Access, 8, 192 440
- Zhu, 2018, Automated attack chain generation using threat intelligence and formal planning, ACM Transactions on Privacy and Security (TOPS), 21, 1
- Li, Building cybersecurity knowledge graphs: A survey, 184
- Marino, Adversarial planning for autonomous cyber agents, 123
- Sattler, 2021, Hierarchical planning for emulated cyber attacks, IEEE Transactions on Network and Service Management, 18, 4524
- Agrafiotis, 2022, Offensive AI agents for autonomous cyber operations, IEEE European Symposium on Security and Privacy Workshops (EuroS&PW)., 186
Cited by
Sorted by citations
Wang, L., Li, Z., Jiang, Y., Wang, Z., Shen, X., Ruan, W., & Chen, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32578-5_3 · Cited by 40
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
“First, dual-use research: the same ReAct loops, plan-and-solve agents, and multi-agent coordination patterns that improve defense are directly usable for unauthorized penetration testing, autonomous exploitation, and red-team automation [22,32–36 , 92].”
A Dynamic AI-Powered Cyber Range for Cybersecurity Awareness and Skill Testing
Shibi Kumar, S., Manasa, K., Nishad, A. K., Nagaraja, S. R., Vincent, R., & Kannadaguli, P. (2026) · Contemporary Computing Innovations Conference (CCIC) · doi:10.1109/ccic68129.2026.11486131
Neto, E. C. P., Iqbal, S., Buffett, S., Sultana, M., & Taylor, A. (2026) · International Journal of Information Security · doi:10.1007/s10207-026-01290-6
Metadata
- Authors
- Loevenich, J. F., & Lopes, R. R. F.
- Affiliations
- Thales (Germany) (DE)
- Venue
- 2025 IEEE 50th Conference on Local Computer Networks (LCN)
- Publisher
- IEEE
- Published
- 2025-10-13
- Pages
- 1-7
- ISSN
- 0742-1303 (ISSN-L)
- OpenAlex
- W4414197409
- Cited by
- 4
- References
- 5
- Citations by year
- 2026: 4
- FWCI
- 4.57
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Conference on Local Computer Networks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- tactical mobile ad hoc networks, red teaming, cybersecurity knowledge graphs, LLM agents, cyber threat intelligence, advanced persistent threats, attack simulation, Metasploit, sliver, military network security, cyber resilience
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
