WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
Abstract
The cross-prompt injection attack (XPIA) is an effective technique that can be used for data exfiltration, and that has seen increasing use. In this attack, the attacker injects a malicious instruction into third party data which an LLM is likely to consume when assisting a user, who is the victim. XPIA is often used as a means for data exfiltration, and the estimated cost of the average data breach for a business is nearly $4.5 million, which includes breaches such as compromised enterprise credentials. With the rise of gradient-based attacks such as the GCG suffix attack, the odds of an XPIA occurring which uses a GCG suffix are worryingly high. As part of my work in Microsoft's AI Red Team, I demonstrated a viable attack model using a GCG suffix paired with an injection in a simulated XPIA scenario. The results indicate that the presence of a GCG suffix can increase the odds of successful data exfiltration by nearly 20%, with some caveats.
Cite
@article{arxiv.2408.00925,
title = {WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes},
author = {Victor Valbuena},
journal= {arXiv preprint arXiv:2408.00925},
year = {2024}
}
Comments
8 pages, 8 figures. Conducted as part of employment at Microsoft Corporation