Score: 0

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

Published: September 5, 2025 | arXiv ID: 2509.09706v1

By: Taniya Gidatkar, Oluwaseun Ajao, Matthew Shardlow

Potential Business Impact:

Makes AI smarter and harder to trick.

Business Areas:
Text Analytics Data and Analytics, Software

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.

Country of Origin
šŸ‡¬šŸ‡§ United Kingdom

Page Count
8 pages

Category
Computer Science:
Cryptography and Security