# Differential Robustness in Transformer Language Models: Empirical Evaluation Under Adversarial Text Attacks

arXiv: https://arxiv.org/abs/2509.09706 · HTML: https://mlsanity.com/paper/2509.09706/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [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)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [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)
- [Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices](https://mlsanity.com/paper/2403.12503/) (2024)
- [A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions](https://mlsanity.com/paper/2405.14487/) (2024)
- [Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2408.04643/) (2024)

## Built on by (most cited first, 1 of 1)

- [Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts](https://mlsanity.com/paper/2510.15973/) (2025)

## Abstract (arXiv)

This study evaluates the resilience of large language models (LLMs) against adversarial attacks, specifically focusing on Flan-T5, BERT, and RoBERTa-Base. Using systematically designed adversarial tests through TextFooler and BERTAttack, we found significant variations in model robustness. RoBERTa-Base and FlanT5 demonstrated remarkable resilience, maintaining accuracy even when subjected to sophisticated attacks, with attack success rates of 0%. In contrast. BERT-Base showed considerable vulnerability, with TextFooler achieving a 93.75% success rate in reducing model accuracy from 48% to just 3%. Our research reveals that while certain LLMs have developed effective defensive mechanisms, these safeguards often require substantial computational resources. This study contributes to the understanding of LLM security by identifying existing strengths and weaknesses in current safeguarding approaches and proposes practical recommendations for developing more efficient and effective defensive strategies.