Skip to content

Is half your workforce breaking AI policy? | The AI Insider Threat Report

Read Now
Uncategorized
18 Oct 2024

Indirect Prompt Injection Attack

Indirect Prompt Injection Attack

Indirect Prompt Injection Attack

An attack in which the attacker inserts malicious content into, for instance, information likely to be included in a response to a prompt; when retrieved, the malicious content causes the AI model to behave in unexpected or harmful ways See Prompt Injection Attack and Passive Prompt Injection Attack

To learn more about our Inference Platform arrange a callback.

Latest Posts

Blog

CalypsoAI Achieves SOC 2 Certification

News

CalypsoAI’s Insider AI Threat Report: 52% of U.S. Employees Are Willing to Break Policy to Use AI

News

Beyond Human Hackers: Agentic AI Becomes the Primary Threat Actor