# Detecting Textual Adversarial Examples through Randomized Substitution and Vote

arXiv: https://arxiv.org/abs/2109.05698 · HTML: https://mlsanity.com/paper/2109.05698/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [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)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://mlsanity.com/paper/1804.06059/) (2018)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Gradient-based Adversarial Attacks against Text Transformers](https://mlsanity.com/paper/2104.13733/) (2021)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Combating Adversarial Misspellings with Robust Word Recognition](https://mlsanity.com/paper/1905.11268/) (2019)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [Crafting Adversarial Input Sequences for Recurrent Neural Networks](https://mlsanity.com/paper/1604.08275/) (2016)
- [Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation](https://mlsanity.com/paper/1909.01492/) (2019)
- [SafetyNet: Detecting and Rejecting Adversarial Examples Robustly](https://mlsanity.com/paper/1704.00103/) (2017)
- [Robustness Verification for Transformers](https://mlsanity.com/paper/2002.06622/) (2020)
- [Towards Robustness Against Natural Language Word Substitutions](https://mlsanity.com/paper/2107.13541/) (2021)
- [Robust Encodings: A Framework for Combating Adversarial Typos](https://mlsanity.com/paper/2005.01229/) (2020)
- [Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification](https://mlsanity.com/paper/1909.03084/) (2019)
- [Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples](https://mlsanity.com/paper/2004.05887/) (2020)
- [Generating Natural Language Attacks in a Hard Label Black Box Setting](https://mlsanity.com/paper/2012.14956/) (2020)
- [Natural Language Adversarial Defense through Synonym Encoding](https://mlsanity.com/paper/1909.06723/) (2019)

## Built on by (most cited first, 8 of 8)

- [Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention](https://mlsanity.com/paper/2311.17400/) (2023)
- [Masked Language Model Based Textual Adversarial Example Detection](https://mlsanity.com/paper/2304.08767/) (2023)
- [The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples](https://mlsanity.com/paper/2305.04067/) (2023)
- [ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation](https://mlsanity.com/paper/2210.12396/) (2022)
- [Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal](https://mlsanity.com/paper/2507.21750/) (2025)
- [Optimal and efficient text counterfactuals using Graph Neural Networks](https://mlsanity.com/paper/2408.01969/) (2024)
- [What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples](https://mlsanity.com/paper/2309.10916/) (2023)
- [Rectifying Adversarial Examples Using Their Vulnerabilities](https://mlsanity.com/paper/2601.00270/) (2026)

## Abstract (arXiv)

A line of work has shown that natural text processing models are vulnerable to adversarial examples. Correspondingly, various defense methods are proposed to mitigate the threat of textual adversarial examples, eg, adversarial training, input transformations, detection, etc. In this work, we treat the optimization process for synonym substitution based textual adversarial attacks as a specific sequence of word replacement, in which each word mutually influences other words. We identify that we could destroy such mutual interaction and eliminate the adversarial perturbation by randomly substituting a word with its synonyms. Based on this observation, we propose a novel textual adversarial example detection method, termed Randomized Substitution and Vote (RS&V), which votes the prediction label by accumulating the logits of k samples generated by randomly substituting the words in the input text with synonyms. The proposed RS&V is generally applicable to any existing neural networks without modification on the architecture or extra training, and it is orthogonal to prior work on making the classification network itself more robust. Empirical evaluations on three benchmark datasets demonstrate that our RS&V could detect the textual adversarial examples more successfully than the existing detection methods while maintaining the high classification accuracy on benign samples.