Differential Robustness in Transformer Language Models: Empirical Evaluation Under Adversarial Text Attacks
By: Taniya Gidatkar, Oluwaseun Ajao, Matthew Shardlow
Potential Business Impact:
Makes AI smarter and harder to trick.
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.
Similar Papers
Adversarial Attack Classification and Robustness Testing for Large Language Models for Code
Software Engineering
Makes computer code safer from tricky words.
An Investigation of Large Language Models and Their Vulnerabilities in Spam Detection
Cryptography and Security
New AI can't always spot tricky spam emails.
Adversarial Question Answering Robustness: A Multi-Level Error Analysis and Mitigation Study
Computation and Language
Makes AI better at answering questions, even tricky ones.