# LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization

arXiv: https://arxiv.org/abs/2505.16008 · HTML: https://mlsanity.com/paper/2505.16008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset](https://mlsanity.com/paper/2108.13897/) (2021)
- [Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review](https://mlsanity.com/paper/2305.16768/) (2023)
- [Text Embedding Inversion Security for Multilingual Language Models](https://mlsanity.com/paper/2401.12192/) (2024)
- [Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries](https://mlsanity.com/paper/2406.10280/) (2024)
- [Bregman Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1306.3203/) (2013)
- [An Accelerated Linearized Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1401.6607/) (2014)
- [Distributed Optimization Using the Primal-Dual Method of Multipliers](https://mlsanity.com/paper/1702.00841/) (2017)
- [Privacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework](https://mlsanity.com/paper/2004.13999/) (2020)
- [Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks](https://mlsanity.com/paper/2408.11749/) (2024)
- [Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis](https://mlsanity.com/paper/2410.13237/) (2024)
- [Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization](https://mlsanity.com/paper/2407.09324/) (2024)
- [Distributed Optimisation with Linear Equality and Inequality Constraints using PDMM](https://mlsanity.com/paper/2309.12897/) (2023)
- [ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation](https://mlsanity.com/paper/2502.11308/) (2025)
- [Distributed Nonlinear Conic Optimisation with partially separable Structure](https://mlsanity.com/paper/2405.09490/) (2024)

## Built on by (most cited first, 1 of 1)

- [SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval](https://mlsanity.com/paper/2606.27976/) (2026)

## Abstract (arXiv)

We propose LAGO - Language Similarity-Aware Graph Optimization - a novel approach for few-shot cross-lingual embedding inversion attacks, addressing critical privacy vulnerabilities in multilingual NLP systems. Unlike prior work in embedding inversion attacks that treat languages independently, LAGO explicitly models linguistic relationships through a graph-based constrained distributed optimization framework. By integrating syntactic and lexical similarity as edge constraints, our method enables collaborative parameter learning across related languages. Theoretically, we show this formulation generalizes prior approaches, such as ALGEN, which emerges as a special case when similarity constraints are relaxed. Our framework uniquely combines Frobenius-norm regularization with linear inequality or total variation constraints, ensuring robust alignment of cross-lingual embedding spaces even with extremely limited data (as few as 10 samples per language). Extensive experiments across multiple languages and embedding models demonstrate that LAGO substantially improves the transferability of attacks with 10-20% increase in Rouge-L score over baselines. This work establishes language similarity as a critical factor in inversion attack transferability, urging renewed focus on language-aware privacy-preserving multilingual embeddings.