Skip to content
Preprint

The TellTail of Embeddings: Fingerprinting Retrievers in Black-Box Systems

Oct 2026 · 0 citations · 87 references
Computer Science

TL;DR

TellTail shows that retrieval-based systems leak the identity of their embedding model---exposing intellectual property and enabling reconnaissance ahead of model-specific attacks such as corpus poisoning.

Abstract

Dense embedding models are core to modern text retrieval, enabling systems ranging from web search to retrieval-augmented generation (RAG). Yet, retrievers are usually deployed within opaque systems, exposing only ranked results, cited sources, or generated answers. This opacity prevents users from verifying which retrievers providers serve and may create a false sense of robustness against retrieval attacks. We show that attackers can infer retrievers'identity only through queries. We introduce TellTail, a fingerprinting attack for identifying retrievers behind black-box systems across a spectrum of access levels. Despite sharing many properties, retrievers can be steered to emit distinct results. When retrieved passages are exposed, TellTail compares retrieval overlap to deduce the underlying model. When only the final generated response is exposed, TellTail optimizes model-specific queries that induce a chosen retrieval behavior on the target retriever but transfer poorly to others. Interestingly, the poor transferability that limits attacks elsewhere is exactly what makes them useful for fingerprinting. We evaluate TellTail using 53 retrievers under three increasingly restrictive settings. TellTail perfectly identifies the deployed retriever from full retrieval rankings; in 94.3% of attempts with unordered top-3 results; and in 92.5% of cases from language-model-generated answers alone. Furthermore, fingerprinting succeeds against a popular RAG system (OpenWebUI). Overall, TellTail shows that retrieval-based systems leak the identity of their embedding model---exposing intellectual property and enabling reconnaissance ahead of model-specific attacks such as corpus poisoning.

View source

Similar papers

Preprint Oct 2026

RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external knowledge bases also introduces new attack surfaces. Existing data extraction attacks against RAG systems rely on either prompt injection, which heavily depends on the generator...

Yuchen Chen, Wei Cheng, Yuan Xiao et al. · 0 citations
Book Open access Nov 2026

PINS: A Pivot-based Intersection Noise Scheme for Dense Embeddings Privacy in Information Retrieval

Modern Information Retrieval (IR) systems, including small and medium-scale ones, often search across millions of documents. In many cases, data owners outsource retrieval to a third-party host to keep the data accessible. Furthermore, IR has also moved toward semantic matching with dense embeddings; although these emb...

F. D. De Faveri, Guglielmo Faggioli, Nicola Ferro · 0 citations
Preprint Oct 2026

Consistency Is the Attack Surface: Detecting Coordinated Retrieval Poisoning with Embedding Geometry

Consistency-based defenses for retrieval-augmented generation (RAG) rest on an assumption that a sparse adversary breaks: a poisoning campaign may modify a negligible fraction of the corpus, yet retrieval concentrates its passages into the reader's context. Across four Natural Questions retrieval seeds, at least one in...

Zeyan Li, Qi-Rong Guo, Jian-Feng Xu · 0 citations

Quantization Enables Private Dense Retrieval against Malicious Service Providers

The results suggest that private dense retrieval is already practical for moderately sized, privacy-sensitive corpora when minute-scale latency is acceptable, and formulates a two-round cryptographic protocol that provides both guarantees.

Louis Tremblay Thibault, Sofiane Azogagh, Marc-Olivier Killijian et al. · 1 citation
Open access Oct 2026

What a Secret Rotation Buys: Exact Retrieval and Measured Leakage in Vector Databases

Vector databases require embedding geometry for similarity search, but that geometry can also support inference. We evaluate keyed orthogonal obfuscation against a snapshot adversary. The practical Walsh–Hadamard construction has no established confidentiality guarantee; its empirical evaluation covers only the tested...

Ionuț Cernica, Nirvana Popescu · 0 citations

From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models

Open-weight large language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification difficult. Existing black-box fingerprints often rely on secret query-key pairs that reproduce predefined responses, and can therefore be easily disrupted by fine-tuning, pr...

Jia-Xin Hong, Yu-Xin Peng, Hong-Yao Yu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.