# DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation

arXiv: https://arxiv.org/abs/1712.05419 · HTML: https://mlsanity.com/paper/1712.05419/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [Certified Robustness to Text Adversarial Attacks by Randomized [MASK]](https://mlsanity.com/paper/2105.03743/) (2021)
- [Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2201.00768/) (2022)
- [Spiking Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/2406.19230/) (2024)
- [R&R: Metric-guided Adversarial Sentence Generation](https://mlsanity.com/paper/2104.08453/) (2021)
- [Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions](https://mlsanity.com/paper/2302.06801/) (2023)
- [Adversarial Machine Learning in Text Analysis and Generation](https://mlsanity.com/paper/2101.08675/) (2021)
- [Synthetic Text Detection: Systemic Literature Review](https://mlsanity.com/paper/2210.06336/) (2022)
- [A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers](https://mlsanity.com/paper/2405.11904/) (2024)
- [ReinforceBug: A Framework to Generate Adversarial Textual Examples](https://mlsanity.com/paper/2103.08306/) (2021)

## Abstract (arXiv)

Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In this work, we introduce DANCin SEQ2SEQ, a GAN-inspired algorithm for adversarial text example generation targeting largely black-box text classifiers. We recast adversarial text example generation as a reinforcement learning problem, and demonstrate that our algorithm offers preliminary but promising steps towards generating semantically meaningful adversarial text examples in a real-world attack scenario.