TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Martin Gubri, Dennis Ulmer, Hwaran Lee, Sangdoo Yun, Seong Joon Oh


Abstract
Large Language Model (LLM) services and models often come with legal rules on *who* can use them and *how* they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and prevent misuse. In this context, we describe the novel fingerprinting problem of Black-box Identity Verification (BBIV). The goal is to determine whether a third-party application uses a certain LLM through its chat function. We propose a method called Targeted Random Adversarial Prompt (TRAP) that identifies the specific LLM in use. We repurpose adversarial suffixes, originally proposed for jailbreaking, to get a pre-defined answer from the target LLM, while other models give random answers. TRAP detects the target LLMs with over 95% true positive rate at under 0.2% false positive rate even after a single interaction. TRAP remains effective even if the LLM has minor changes that do not significantly alter the original function.
Anthology ID:
2024.findings-acl.683
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11496–11517
Language:
URL:
https://aclanthology.org/2024.findings-acl.683
DOI:
10.18653/v1/2024.findings-acl.683
Bibkey:
Cite (ACL):
Martin Gubri, Dennis Ulmer, Hwaran Lee, Sangdoo Yun, and Seong Joon Oh. 2024. TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11496–11517, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification (Gubri et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.683.pdf