Tailored queries enable identification of the embedding model used by a black-box IR system from the unordered set of retrieved documents, even when a reranker is present.
Kornaropoulos, and Giuseppe Ateniese
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 4roles
background 1polarities
background 1representative citing papers
SeedPrints fingerprints LLMs using persistent biases from initialization seeds for lineage verification across pretraining and adaptation stages.
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
Proposes evidence-bound LLM gateway using attested runtime for verifiable path provenance and policy enforcement.
citing papers explorer
-
Embedding Inference Attack
Tailored queries enable identification of the embedding model used by a black-box IR system from the unordered set of retrieved documents, even when a reranker is present.
-
SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
SeedPrints fingerprints LLMs using persistent biases from initialization seeds for lineage verification across pretraining and adaptation stages.
-
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
-
Evidence-Bound Gateway-Path Provenance for Third-Party LLM Inference
Proposes evidence-bound LLM gateway using attested runtime for verifiable path provenance and policy enforcement.