# Semantic Leakage from Image Embeddings

Source: [Semantic Leakage from Image Embeddings](<https://www.sota2.com/research/paper/69802f83a8b01e76cc8e15f4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-04T05:00:24.095Z

Authors: Yiyi Chen, Qiongkai Xu, Desmond Elliott, Qiongxiu Li, Johannes Bjerva

Published: 2026-01-30T12:46:41.000Z

## Abstract

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprisingly, we show that semantic leakage does not require exact reconstruction of the original image. Preserving local semantic neighborhoods under embedding alignment is sufficient to expose the intrinsic vulnerability of image embeddings. Crucially, this preserved neighborhood structure allows semantic information to propagate through a sequence of lossy mappings. Based on this conjecture, we propose Semantic Leakage from Image Embeddings (SLImE), a lightweight inference framework that reveals semantic information from standalone compressed image embeddings, incorporating a locally trained semantic retriever with off-the-shelf models, without training task-specific decoders. We thoroughly validate each step of the framework empirically, from aligned embeddings to retrieved tags, symbolic representations, and grammatical and coherent descriptions. We evaluate SLImE across a range of open and closed embedding models, including GEMINI, COHERE, NOMIC, and CLIP, and demonstrate consistent recovery of semantic information across diverse inference tasks. Our results reveal a fundamental vulnerability in image embeddings, whereby the preservation of semantic neighborhoods under alignment enables semantic leakage, highlighting challenges for privacy preservation.1

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.22929>)

[PDF](<https://arxiv.org/pdf/2601.22929.pdf>)
