# Adversarial Black-Box Attacks On Text Classifiers Using Multi-Objective Genetic Optimization Guided By Deep Networks

arXiv: https://arxiv.org/abs/2011.03901 · HTML: https://mlsanity.com/paper/2011.03901/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2020.

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

- [Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization](https://mlsanity.com/paper/2111.01528/) (2021)
- [Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations](https://mlsanity.com/paper/2201.06384/) (2022)
- [Enhancing Robustness of AI Offensive Code Generators via Data Augmentation](https://mlsanity.com/paper/2306.05079/) (2023)

## Abstract (arXiv)

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic search with multi-objective optimization guided by deep learning based inferences and Seq2Seq mutation to generate semantically similar but imperceptible adversaries. We compare our approach with DeepWordBug (DWB) on SST and IMDB sentiment datasets by attacking three trained models viz. char-LSTM, word-LSTM and elmo-LSTM. On an average, we achieve an attack success rate of 65.67% for SST and 36.45% for IMDB across the three models showing an improvement of 49.48% and 101% respectively. Furthermore, our qualitative study indicates that 94% of the time, the users were not able to distinguish between an original and adversarial sample.