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

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification Martin Gubri author Dennis Ulmer author Hwaran Lee author Sangdoo Yun author Seong Joon Oh author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication gubri-etal-2024-trap 10.18653/v1/2024.findings-acl.683 https://aclanthology.org/2024.findings-acl.683/ 2024-08 11496 11517