Data exfiltration
A type of AI system attack which attempts to have the system send private data outside your company or to anyone not permitted to see it.
Permissions are the strongest defense: an agent that can't access sensitive data, or can't send anything out, can't leak it. Guardrails reduce the risk but can't make this attack impossible.
Also called
- Data leakage
- Data leak
Kind of
- AI security The practice of defending an AI system, and the data and tools it can reach, from attackers and deliberate misuse.
Related
- Output guardrail A guardrail that checks or filters what comes out of a model before anyone sees it or it takes effect.
- PII redaction A type of guardrail that removes or masks personal data in text passing through a system, usually before it reaches a model or log.
- Indirect prompt injection A type of prompt injection where instructions are hidden in content that the AI system reads (web page, email, file, etc.).
How it connects
- Data exfiltration is best stopped by Least privilege for AI