# Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

arXiv: https://arxiv.org/abs/2203.11199 · HTML: https://mlsanity.com/paper/2203.11199/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Builds on (most cited first, 28 of 28)

- [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)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [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)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [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)
- [Contextualized Perturbation for Textual Adversarial Attack](https://mlsanity.com/paper/2009.07502/) (2020)
- [Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples](https://mlsanity.com/paper/1803.05787/) (2018)
- [Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation](https://mlsanity.com/paper/1909.01492/) (2019)
- [Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression](https://mlsanity.com/paper/1705.02900/) (2017)
- [Imitation Attacks and Defenses for Black-box Machine Translation Systems](https://mlsanity.com/paper/2004.15015/) (2020)
- [SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/2005.14424/) (2020)
- [Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification](https://mlsanity.com/paper/1909.03084/) (2019)
- [Generating Natural Language Attacks in a Hard Label Black Box Setting](https://mlsanity.com/paper/2012.14956/) (2020)
- [MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models](https://mlsanity.com/paper/2009.01048/) (2020)
- [The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations](https://mlsanity.com/paper/1707.08172/) (2017)
- [A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/2010.01345/) (2020)
- [A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks](https://mlsanity.com/paper/2011.10492/) (2020)

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

- [Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text](https://mlsanity.com/paper/2305.16444/) (2023)
- [DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization](https://mlsanity.com/paper/2306.15164/) (2023)
- [VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations](https://mlsanity.com/paper/2306.01273/) (2023)

## Abstract (arXiv)

Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs are not robust. However, we find that the adversarial samples that PrLMs fail are mostly non-natural and do not appear in reality. We question the validity of current evaluation of robustness of PrLMs based on these non-natural adversarial samples and propose an anomaly detector to evaluate the robustness of PrLMs with more natural adversarial samples. We also investigate two applications of the anomaly detector: (1) In data augmentation, we employ the anomaly detector to force generating augmented data that are distinguished as non-natural, which brings larger gains to the accuracy of PrLMs. (2) We apply the anomaly detector to a defense framework to enhance the robustness of PrLMs. It can be used to defend all types of attacks and achieves higher accuracy on both adversarial samples and compliant samples than other defense frameworks.