# Adversarial Text Generation with Dynamic Contextual Perturbation

arXiv: https://arxiv.org/abs/2506.09148 · HTML: https://mlsanity.com/paper/2506.09148/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [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)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Text Understanding from Scratch](https://mlsanity.com/paper/1502.01710/) (2015)
- [A Modified Word Saliency-Based Adversarial Attack on Text Classification Models](https://mlsanity.com/paper/2403.11297/) (2024)
- [Are Synonym Substitution Attacks Really Synonym Substitution Attacks?](https://mlsanity.com/paper/2210.02844/) (2022)
- [SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator](https://mlsanity.com/paper/2403.11833/) (2024)
- [Adversarial Evasion Attack Efficiency against Large Language Models](https://mlsanity.com/paper/2406.08050/) (2024)
- [Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation](https://mlsanity.com/paper/2406.19413/) (2024)

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

- [Text Adversarial Attacks with Dynamic Outputs](https://mlsanity.com/paper/2509.22393/) (2025)
- [When Verification Fails: How Compositionally Infeasible Claims Escape Rejection](https://mlsanity.com/paper/2604.10990/) (2026)

## Abstract (arXiv)

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations, overlooking the broader context, which results in detectable or semantically inconsistent perturbations. We propose a novel adversarial text attack scheme named Dynamic Contextual Perturbation (DCP). DCP dynamically generates context-aware perturbations across sentences, paragraphs, and documents, ensuring semantic fidelity and fluency. Leveraging the capabilities of pre-trained language models, DCP iteratively refines perturbations through an adversarial objective function that balances the dual objectives of inducing model misclassification and preserving the naturalness of the text. This comprehensive approach allows DCP to produce more sophisticated and effective adversarial examples that better mimic natural language patterns. Our experimental results, conducted on various NLP models and datasets, demonstrate the efficacy of DCP in challenging the robustness of state-of-the-art NLP systems. By integrating dynamic contextual analysis, DCP significantly enhances the subtlety and impact of adversarial attacks. This study highlights the critical role of context in adversarial attacks and lays the groundwork for creating more robust NLP systems capable of withstanding sophisticated adversarial strategies.