# A Generative Adversarial Attack for Multilingual Text Classifiers

arXiv: https://arxiv.org/abs/2401.08255 · HTML: https://mlsanity.com/paper/2401.08255/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 15 of 15)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [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)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [The Multilingual Amazon Reviews Corpus](https://mlsanity.com/paper/2010.02573/) (2020)
- [Universal Adversarial Attacks with Natural Triggers for Text Classification](https://mlsanity.com/paper/2005.00174/) (2020)
- [Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework](https://mlsanity.com/paper/2110.15317/) (2021)
- [Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples](https://mlsanity.com/paper/2009.06368/) (2020)
- [Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering](https://mlsanity.com/paper/2104.07646/) (2021)
- [AdvCodeMix: Adversarial Attack on Code-Mixed Data](https://mlsanity.com/paper/2111.00350/) (2021)

## Abstract (arXiv)

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is monolingual and cannot be used to target multilingual victim models, a significant limitation given the increased use of these models. For this reason, in this work we propose an approach to fine-tune a multilingual paraphrase model with an adversarial objective so that it becomes able to generate effective adversarial examples against multilingual classifiers. The training objective incorporates a set of pre-trained models to ensure text quality and language consistency of the generated text. In addition, all the models are suitably connected to the generator by vocabulary-mapping matrices, allowing for full end-to-end differentiability of the overall training pipeline. The experimental validation over two multilingual datasets and five languages has shown the effectiveness of the proposed approach compared to existing baselines, particularly in terms of query efficiency. We also provide a detailed analysis of the generated attacks and discuss limitations and opportunities for future research.