# Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right

arXiv: https://arxiv.org/abs/2507.03473 · HTML: https://mlsanity.com/paper/2507.03473/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation](https://mlsanity.com/paper/1808.07048/) (2018)
- [What Kind of Language Is Hard to Language-Model?](https://mlsanity.com/paper/1906.04726/) (2019)
- [The Grey Hoodie Project: Big Tobacco, Big Tech, and the threat on academic integrity](https://mlsanity.com/paper/2009.13676/) (2020)
- [Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding](https://mlsanity.com/paper/2406.15481/) (2024)
- [Goldfish: Monolingual Language Models for 350 Languages](https://mlsanity.com/paper/2408.10441/) (2024)
- [What a Creole Wants, What a Creole Needs](https://mlsanity.com/paper/2206.00437/) (2022)
- [Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers](https://mlsanity.com/paper/2305.19474/) (2023)
- [Phrase-level Textual Adversarial Attack with Label Preservation](https://mlsanity.com/paper/2205.10710/) (2022)
- [Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages](https://mlsanity.com/paper/2305.08487/) (2023)
- [A Principled Framework for Evaluating on Typologically Diverse Languages](https://mlsanity.com/paper/2407.05022/) (2024)
- [Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks](https://mlsanity.com/paper/2408.11749/) (2024)
- [Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages -- A Singlish Case Study](https://mlsanity.com/paper/2502.12485/) (2025)
- [Arabic Synonym BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2402.03477/) (2024)

## Built on by (most cited first, 2 of 2)

- [QQ: A Language Metadata Toolkit for Multilingual NLP](https://mlsanity.com/paper/2603.00620/) (2026)
- [Variation is the Norm: Embracing Sociolinguistics in NLP](https://mlsanity.com/paper/2603.24222/) (2026)

## Abstract (arXiv)

Despite mounting evidence that multilinguality can be easily weaponized against language models (LMs), works across NLP Security remain overwhelmingly English-centric. In terms of securing LMs, the NLP norm of "English first" collides with standard procedure in cybersecurity, whereby practitioners are expected to anticipate and prepare for worst-case outcomes. To mitigate worst-case outcomes in NLP Security, researchers must be willing to engage with the weakest links in LM security: lower-resourced languages. Accordingly, this work examines the security of LMs for lower- and medium-resourced languages. We extend existing adversarial attacks for up to 70 languages to evaluate the security of monolingual and multilingual LMs for these languages. Through our analysis, we find that monolingual models are often too small in total number of parameters to ensure sound security, and that while multilinguality is helpful, it does not always guarantee improved security either. Ultimately, these findings highlight important considerations for more secure deployment of LMs, for communities of lower-resourced languages.