Whitepapers
This guide builds on the OWASP Agentic AI – Threats and Mitigations publication, our master agentic threat taxonomy, by applying its threat taxonomy to real-world multi-agent systems (MAS). These systems, characterized by multiple autonomous agents coordinating to achieve shared or distributed goals, introduce additional complexity and new attack surfaces.
Multi-Agentic system Threat Modeling Guide v1.0 Read Post »
Это обновление — актуальный и всеобъемлющий ресурс, который охватывает ключевые риски, уязвимости и методы их устранения для защиты генеративного ИИ и LLM-приложений на всех этапах их жизненного цикла: разработки, развертывания и управления. Независимо от того, работаете ли вы с RAG-приложениями, агентными архитектурами или сложными интеграциями LLM, этот список будет полезен разработчикам, специалистам по безопасности и
OWASP Top 10 для LLM и генеративного ИИ (2025) Read Post »
Esta atualização oferece um recurso abrangente e atualizado que aborda os principais riscos, vulnerabilidades e medidas de proteção para garantir a segurança das aplicações de IA Generativa e LLMs em todo o seu ciclo de vida de desenvolvimento, implantação e gestão. Se você trabalha com aplicações baseadas em RAG, arquiteturas com agentes ou integrações complexas
OWASP Top 10 para Aplicações de LLM e IA Generativa (2025) Read Post »
此次更新提供了一个全面的资源，针对在生成式AI和大型语言模型应用程序的开发、部署和管理生命周期中的主要风险、漏洞和缓解措施进行了解决。无论您是处理基于RAG的应用程序、代理架构，还是复杂的大型语言模型集成，这份清单对于开发人员、安全专业人员和希望安全采用AI的组织来说，都是必不可少的。
OWASP大型语言模型与生成式AI十大风险（2025） Read Post »
這次更新針對生成式AI和大型語言模型應用在開發、部署和管理生命週期提供了一個全新且全面的資源，其中的針對主要風險、弱點和緩解措施進行了新的詮釋及說明。無論您是使用基於 RAG 的應用、代理架構，或是複雜的大型語言模型整合，這份清單對於開發人員、資安專家以及希望安全採用 AI 的組織來說都是不可或缺的參考資料。
OWASP大型語言模型及生成式 AI 十大風險（2025) Read Post »
Dieses Update bietet eine aktualisierte und umfassende Ressource, die sich mit den größten Risiken, Schwachstellen und Gegenmaßnahmen für die Absicherung von Anwendungen für generative KI und LLM über ihren gesamten Entwicklungs-, Bereitstellungs- und Verwaltungslebenszyklus hinweg befasst. Ganz gleich, ob Sie mit RAG-basierten Anwendungen, Agentic-Architekturen oder komplexen LLM-Integrationen arbeiten, diese Liste ist ein Muss für Entwickler,
die OWASP Top 10 für LLM & Generative KI (2025) Read Post »
El OWASP Top 10 para Aplicaciones de Modelos de Lenguaje Grandes comenzó en 2023 como un esfuerzo impulsado por la comunidad para resaltar y abordar problemas de seguridad específicos para aplicaciones de IA. Desde ese momento, la tecnología ha seguido extendiéndose a través de industrias y aplicaciones, al igual que los riesgos asociados. A medida
Top 10 2025 de riesgos y mitigaciones para LLMs y aplicaciones de IA Generativa Read Post »
This paper examines the practical implications of large language models (LLMs) in offensive cybersecurity, moving beyond theoretical possibilities to assess their real-world effectiveness. The research, conducted by the CTI Layer Team at OWASP Top Ten For LLMs, explores the ability of LLMs such as GPT-4o, Claude, and DeepSeek r-1 to exploit vulnerabilities in the OWASP
OWASP LLM Exploit Generation v1.0 Read Post »
Agentic AI represents an advancement in autonomous systems, increasingly enabled by large language models (LLMs) and generative AI. While agentic AI predates modern LLMs, their integration with generative AI has significantly expanded their scale, capabilities, and associated risks. This document is the first in a series of guides from the OWASP Agentic Security Initiative (ASI)
Agentic AI – Threats and Mitigations Read Post »
The rapid proliferation of Large Language Models (LLMs) across various industries has highlighted the critical need for advanced data security practices. As these AI systems become more sophisticated, they bring with them unprecedented risks, including potential breaches of sensitive information and challenges in meeting stringent data protection regulations. This white paper outlines a comprehensive set
LLM and Gen AI Data Security Best Practices Read Post »
