RedTeamLLM: an Agentic AI framework for offensive security

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Challita, Brian, Parrend, Pierre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909607371210752
author Challita, Brian
Parrend, Pierre
author_facet Challita, Brian
Parrend, Pierre
contents From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity. This novel framework addresses four open challenges: plan correction, memory management, context window constraint, and generality vs. specialization. Evaluation is performed through the automated resolution of a range of entry-level, but not trivial, CTF challenges. The contribution of the reasoning capability of our agentic AI framework is specifically evaluated.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06913
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RedTeamLLM: an Agentic AI framework for offensive security
Challita, Brian
Parrend, Pierre
Cryptography and Security
Artificial Intelligence
Computers and Society
From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity. This novel framework addresses four open challenges: plan correction, memory management, context window constraint, and generality vs. specialization. Evaluation is performed through the automated resolution of a range of entry-level, but not trivial, CTF challenges. The contribution of the reasoning capability of our agentic AI framework is specifically evaluated.
title RedTeamLLM: an Agentic AI framework for offensive security
topic Cryptography and Security
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2505.06913