TABLE OF CONTENTS

Explore the top 10 security vulnerabilities affecting Large Language Models. Click on any topic to learn more or use the navigation below to read from start to finish.

01

Prompt Injection

Manipulating AI behavior through carefully crafted inputs

02

Sensitive Information Disclosure

When AI systems reveal private or protected data

03

Supply Chain

Vulnerabilities in the components used to build AI systems

04

Data and Model Poisoning

Corrupting training data or models for malicious purposes

05

Improper Output Handling

When AI outputs are used insecurely in downstream systems