From 9252d6fc7aaa4c811fc0de8e7763f71830ccc815 Mon Sep 17 00:00:00 2001 From: Matteo Meucci Date: Sun, 16 Nov 2025 17:52:13 +0100 Subject: [PATCH] Update 2.1.1_Architectural_Mapping_of_OWASP_Threats.md --- .../content/2.1.1_Architectural_Mapping_of_OWASP_Threats.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Document/content/2.1.1_Architectural_Mapping_of_OWASP_Threats.md b/Document/content/2.1.1_Architectural_Mapping_of_OWASP_Threats.md index 25a5d9e..5fc40ca 100644 --- a/Document/content/2.1.1_Architectural_Mapping_of_OWASP_Threats.md +++ b/Document/content/2.1.1_Architectural_Mapping_of_OWASP_Threats.md @@ -8,7 +8,7 @@ By examining the AI architecture across its four core layers, data, infrastructu AI Architecture Threat Model

-**Fig. 2 Threat Model of OWASP Threats (LLM T10 and AI Exchange) Mapped to Impacted AI Components of a SAIF baseline architecture** +*Fig. 2 Threat Model of OWASP Threats (LLM T10 and AI Exchange) mapped to impacted AI components of a SAIF baseline architecture* We use a structured process for identifying potential threats to an AI system by analyzing its architecture and operational context. In this approach, we reference threat categories defined by OWASP, specifically the *OWASP Top 10 for LLM* and *OWASP AI Exchange* to identify risks such as prompt injection, data poisoning, and model evasion. For each identified threat, we outline a representative threat scenario to highlight which system components are impacted. This mapping helps derive targeted test cases aimed at uncovering exploitable vulnerabilities and weaknesses.