# AdvCodeMix: Adversarial Attack on Code-Mixed Data

arXiv: https://arxiv.org/abs/2111.00350 · HTML: https://mlsanity.com/paper/2111.00350/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 30 Oct 2021.

## Builds on (most cited first, 16 of 16)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets](https://mlsanity.com/paper/2008.04277/) (2020)
- [Sentiment Analysis of Code-Mixed Indian Languages: An Overview of SAIL_Code-Mixed Shared Task @ICON-2017](https://mlsanity.com/paper/1803.06745/) (2018)
- [Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots](https://mlsanity.com/paper/2103.09593/) (2021)
- [Natural Backdoor Attack on Text Data](https://mlsanity.com/paper/2006.16176/) (2020)
- [Preparing Bengali-English Code-Mixed Corpus for Sentiment Analysis of Indian Languages](https://mlsanity.com/paper/1803.04000/) (2018)
- [kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification](https://mlsanity.com/paper/2009.03673/) (2020)
- [Palomino-Ochoa at SemEval-2020 Task 9: Robust System based on Transformer for Code-Mixed Sentiment Classification](https://mlsanity.com/paper/2011.09448/) (2020)
- [Language Identification of Bengali-English Code-Mixed data using Character & Phonetic based LSTM Models](https://mlsanity.com/paper/1803.03859/) (2018)

## Built on by (most cited first, 3 of 3)

- [Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text](https://mlsanity.com/paper/2506.14012/) (2025)
- [Elevating Code-mixed Text Handling through Auditory Information of Words](https://mlsanity.com/paper/2310.18155/) (2023)
- [A Generative Adversarial Attack for Multilingual Text Classifiers](https://mlsanity.com/paper/2401.08255/) (2024)

## Abstract (arXiv)

Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have explained the first generalized framework on text perturbation to attack code-mixed classification models in a black-box setting. We rely on various perturbation techniques that preserve the semantic structures of the sentences and also obscure the attacks from the perception of a human user. The present methodology leverages the importance of a token to decide where to attack by employing various perturbation strategies. We test our strategies on various sentiment classification models trained on Bengali-English and Hindi-English code-mixed datasets, and reduce their F1-scores by nearly 51 % and 53 % respectively, which can be further reduced if a larger number of tokens are perturbed in a given sentence.