Empirical study reporting 98% base-model attribution accuracy and cross-encoder fingerprinting of unseen system prompts (AUC 0.768 single-conversation, 0.943 with 50 conversations) in black-box LLM agents.
Lingjiao Chen, Matei Zaharia, and James Zou
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Black-Box Forensics for Conversational LLM Agents
Empirical study reporting 98% base-model attribution accuracy and cross-encoder fingerprinting of unseen system prompts (AUC 0.768 single-conversation, 0.943 with 50 conversations) in black-box LLM agents.