# basics
標記為「basics」的 16 篇文章
Transformer Architecture Basics for Security
Understanding transformer architecture fundamentals through a security lens: how attention, embeddings, and generation create exploitable properties.
Lab: Basic RAG System Security Testing
Introduction to testing Retrieval-Augmented Generation systems for document injection and retrieval manipulation vulnerabilities.
Conversation History Analysis
Analyze how conversation history influences model behavior and identify opportunities for context manipulation.
Embedding Basics for Security
Understand text embeddings and their security relevance by generating, comparing, and manipulating embedding vectors.
Lab: Multimodal Input Testing Basics
Introduction to testing multimodal LLMs with image and text inputs to understand cross-modal behavior.
Response Analysis Fundamentals
Learn to analyze LLM responses for information leakage, inconsistencies, and indicators of safety mechanism activation.
Basic Indirect Prompt Injection
Plant and trigger a basic indirect prompt injection payload in content consumed by an LLM.
Completion Hijacking Fundamentals
Craft partial sentences that steer model completions toward attacker-desired outputs.
Transformer Architecture Basics for 安全
Understanding transformer architecture fundamentals through a security lens: how attention, embeddings, and generation create exploitable properties.
實驗室: Basic RAG System 安全 Testing
介紹 to testing Retrieval-Augmented Generation systems for document injection and retrieval manipulation vulnerabilities.
Conversation History Analysis
Analyze how conversation history influences model behavior and identify opportunities for context manipulation.
Embedding Basics for 安全
Understand text embeddings and their security relevance by generating, comparing, and manipulating embedding vectors.
實驗室: Multimodal Input Testing Basics
介紹 to testing multimodal LLMs with image and text inputs to understand cross-modal behavior.
Response Analysis 基礎
Learn to analyze LLM responses for information leakage, inconsistencies, and indicators of safety mechanism activation.
Basic Indirect 提示詞注入
Plant and trigger a basic indirect prompt injection payload in content consumed by an LLM.
Completion Hijacking 基礎
Craft partial sentences that steer model completions toward attacker-desired outputs.