# gemini
標記為「gemini」的 16 篇文章
Case Study: Prompt Injection Attacks on Google Bard/Gemini
Analysis of prompt injection vulnerabilities discovered in Google Bard (later Gemini), including indirect injection through Google Workspace integration and the unique attack surface created by multimodal capabilities.
GCP Vertex AI Security Assessment
Security assessment methodology for GCP Vertex AI covering IAM bindings, VPC Service Controls, Model Garden risks, and detection strategies for Gemini API abuse.
Gemini Attack Surface
Gemini-specific attack vectors including multimodal injection across image, audio, and video inputs, Google Workspace integration attacks, grounding abuse, and code execution exploitation.
Gemini (Google) Overview
Architecture overview of Google's Gemini model family, including natively multimodal design, long context capabilities, Google ecosystem integration, and security-relevant features for red teaming.
Gemini Known Vulnerabilities
Documented Gemini vulnerabilities including image generation bias incidents, system prompt extraction, safety filter inconsistencies, multimodal injection exploits, and grounding abuse.
Gemini Testing Methodology
Systematic methodology for red teaming Gemini, including Vertex AI API probing, Google AI Studio testing, multimodal test case design, and grounding attack validation.
Gemini Architecture Security Analysis
Deep security analysis of Gemini's native multimodal architecture and long-context capabilities.
Testing Google Gemini: Complete Guide
Complete red team testing guide for Google's Gemini including multimodal inputs and long context.
Case Study: 提示詞注入 攻擊s on Google Bard/Gemini
Analysis of prompt injection vulnerabilities discovered in Google Bard (later Gemini), including indirect injection through Google Workspace integration and the unique attack surface created by multimodal capabilities.
GCP Vertex AI 安全 評量
安全 assessment methodology for GCP Vertex AI covering IAM bindings, VPC Service Controls, 模型 Garden risks, and detection strategies for Gemini API abuse.
Gemini 攻擊面
Gemini 特有攻擊向量，含跨圖像、音訊與視訊輸入之多模態注入、Google Workspace 整合攻擊、接地濫用，與程式碼執行利用。
Gemini（Google）概觀
Google Gemini 模型家族的架構概觀，包括原生多模態設計、長上下文能力、Google 生態整合，以及對紅隊具意義的安全相關特性。
Gemini 已知漏洞
已記錄的 Gemini 漏洞，包括影像生成偏見事件、系統提示擷取、安全過濾不一致、多模態注入 exploit，以及 grounding 濫用。
Gemini Testing Methodology
Systematic methodology for red teaming Gemini, including Vertex AI API probing, Google AI Studio testing, multimodal test case design, and grounding attack validation.
Gemini Architecture 安全 Analysis
Deep security analysis of Gemini's native multimodal architecture and long-context capabilities.
Testing Google Gemini: Complete 指南
Complete red team testing guide for Google's Gemini including multimodal inputs and long context.