mlsanityData to 14 Oct 2026

WHITE PAPER: A Brief Exploration of Data Exfiltration using GCG Suffixes

arXiv 2408.00925 ↗First posted 1 Aug 2024cs.CR cs.AIcited by 0

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

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  2. 2024Get my drift? Catching LLM Task Drift with Activation Deltascited by 72

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
  2. 2025Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems
  3. 2025Prompt Injection 2.0: Hybrid AI Threats
  4. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
  5. 2025XBreaking: Understanding how LLMs security alignment can be broken
  6. 2025EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
  7. 2023Prompt Injection attack against LLM-integrated Applications
  8. 2025Cybersecurity AI: Hacking the AI Hackers via Prompt Injection