- Tactics
- Initial Access
- Maturity
- demonstrated
- Reference
- atlas.mitre.org/techniques/AML.T0078
Description
Adversaries may gain access to an AI system through a user visiting a website over the normal course of browsing, or an AI agent retrieving information from the web on behalf of a user. Websites can contain an LLM Prompt Injection which, when executed, can change the behavior of the AI model.
The same approach may be used to deliver other types of malicious code that don’t target AI directly (See Drive-by Compromise in ATT&CK).
How GTK Cyber trains on this
GTK Cyber's hands-on AI security courses cover adversarial-AI techniques across the MITRE ATLAS framework, including the Initial Access tactic this technique falls under. Our practitioner-led training is taught by Charles Givre and other field-tested SMEs and focuses on real adversarial scenarios, not slide decks.