# Assessing Robustness of Text Classification through Maximal Safe Radius Computation

arXiv: https://arxiv.org/abs/2010.02004 · HTML: https://mlsanity.com/paper/2010.02004/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [On Guaranteed Optimal Robust Explanations for NLP Models](https://mlsanity.com/paper/2105.03640/) (2021)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [The King is Naked: on the Notion of Robustness for Natural Language Processing](https://mlsanity.com/paper/2112.07605/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [When to Trust AI: Advances and Challenges for Certification of Neural Networks](https://mlsanity.com/paper/2309.11196/) (2023)
- [Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective](https://mlsanity.com/paper/2204.12316/) (2022)
- [On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations](https://mlsanity.com/paper/2201.00318/) (2022)
- [Emergent Linguistic Structures in Neural Networks are Fragile](https://mlsanity.com/paper/2210.17406/) (2022)
- [Jailbreaking Large Language Models in Infinitely Many Ways](https://mlsanity.com/paper/2501.10800/) (2025)
- [Perturbation-based Self-supervised Attention for Attention Bias in Text Classification](https://mlsanity.com/paper/2305.15684/) (2023)

## Abstract (arXiv)

Neural network NLP models are vulnerable to small modifications of the input that maintain the original meaning but result in a different prediction. In this paper, we focus on robustness of text classification against word substitutions, aiming to provide guarantees that the model prediction does not change if a word is replaced with a plausible alternative, such as a synonym. As a measure of robustness, we adopt the notion of the maximal safe radius for a given input text, which is the minimum distance in the embedding space to the decision boundary. Since computing the exact maximal safe radius is not feasible in practice, we instead approximate it by computing a lower and upper bound. For the upper bound computation, we employ Monte Carlo Tree Search in conjunction with syntactic filtering to analyse the effect of single and multiple word substitutions. The lower bound computation is achieved through an adaptation of the linear bounding techniques implemented in tools CNN-Cert and POPQORN, respectively for convolutional and recurrent network models. We evaluate the methods on sentiment analysis and news classification models for four datasets (IMDB, SST, AG News and NEWS) and a range of embeddings, and provide an analysis of robustness trends. We also apply our framework to interpretability analysis and compare it with LIME.