# TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

arXiv: https://arxiv.org/abs/2212.09254 · HTML: https://mlsanity.com/paper/2212.09254/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 64 references that are in the map.
- First posted on arXiv 19 Dec 2022.

## Builds on (most cited first, 30 of 51)

- [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)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Unlabeled Data Improves Adversarial Robustness](https://mlsanity.com/paper/1905.13736/) (2019)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)

## Built on by (most cited first, 21 of 21)

- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [Attacking Large Language Models with Projected Gradient Descent](https://mlsanity.com/paper/2402.09154/) (2024)
- [A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion](https://mlsanity.com/paper/2303.16378/) (2023)
- [Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models](https://mlsanity.com/paper/2404.02928/) (2024)
- [DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization](https://mlsanity.com/paper/2408.11071/) (2024)
- [Task Facet Learning: A Structured Approach to Prompt Optimization](https://mlsanity.com/paper/2406.10504/) (2024)
- [Advancing the Robustness of Large Language Models through Self-Denoised Smoothing](https://mlsanity.com/paper/2404.12274/) (2024)
- [REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective](https://mlsanity.com/paper/2502.17254/) (2025)
- [LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning](https://mlsanity.com/paper/2506.15606/) (2025)
- [Single-pass Detection of Jailbreaking Input in Large Language Models](https://mlsanity.com/paper/2502.15435/) (2025)
- [CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary](https://mlsanity.com/paper/2501.15562/) (2025)
- [Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards](https://mlsanity.com/paper/2508.05658/) (2025)
- [Revisiting Character-level Adversarial Attacks for Language Models](https://mlsanity.com/paper/2405.04346/) (2024)
- [What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale](https://mlsanity.com/paper/2504.14815/) (2025)
- [The Power of Few: Accelerating and Enhancing Data Reweighting with Coreset Selection](https://mlsanity.com/paper/2403.12166/) (2024)
- [Robustness in Both Domains: CLIP Needs a Robust Text Encoder](https://mlsanity.com/paper/2506.03355/) (2025)
- [Is Certifying ℓp Robustness Still Worthwhile?](https://mlsanity.com/paper/2310.09361/) (2023)
- [Optimizing Large Language Models for Dynamic Constraints through Human-in-the-Loop Discriminators](https://mlsanity.com/paper/2410.15163/) (2024)
- [OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks](https://mlsanity.com/paper/2608.29568/) (2026)

## Abstract (arXiv)

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP). However, in contrast to the computer vision domain where the first-order projected gradient descent (PGD) is used as the benchmark approach to generate adversarial examples for robustness evaluation, there lacks a principled first-order gradient-based robustness evaluation framework in NLP. The emerging optimization challenges lie in 1) the discrete nature of textual inputs together with the strong coupling between the perturbation location and the actual content, and 2) the additional constraint that the perturbed text should be fluent and achieve a low perplexity under a language model. These challenges make the development of PGD-like NLP attacks difficult. To bridge the gap, we propose TextGrad, a new attack generator using gradient-driven optimization, supporting high-accuracy and high-quality assessment of adversarial robustness in NLP. Specifically, we address the aforementioned challenges in a unified optimization framework. And we develop an effective convex relaxation method to co-optimize the continuously-relaxed site selection and perturbation variables and leverage an effective sampling method to establish an accurate mapping from the continuous optimization variables to the discrete textual perturbations. Moreover, as a first-order attack generation method, TextGrad can be baked into adversarial training to further improve the robustness of NLP models. Extensive experiments are provided to demonstrate the effectiveness of TextGrad not only in attack generation for robustness evaluation but also in adversarial defense.