WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 2 of its 5 references that are in the map. First posted on arXiv 1 Aug 2024.
Builds on
2 of 5 references.
References · 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
- 2025Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems
- 2025Prompt Injection 2.0: Hybrid AI Threats
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- 2025XBreaking: Understanding how LLMs security alignment can be broken
- 2025EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
- 2023Prompt Injection attack against LLM-integrated Applications
- 2025Cybersecurity AI: Hacking the AI Hackers via Prompt Injection