Exploring Adversarial Robustness in Classification tasks using DNA Language Models

Abstract: DNA LLMs, such as GROVER, DNABERT2 and the Nucleotide Transformer, operate on DNA sequences that inherently contain sequencing errors, mutations, and laboratory-induced noise, which may significantly impact model performance. Despite the importance of this issue, the robustness of DNA LLMs remains largely underexplored. In this paper, we comprehensivly investigate their robustness in DNA classification by applying various adversarial attack strategies: the character (nucleotide substitutions), word (codon modifications), and sentence levels (back-translation-based transformations) to systematically analyze model vulnerabilities. Our results demonstrate that DNA LLMs are highly susceptible to adversarial attacks, leading to significant performance degradation. Furthermore, we explore adversarial training method as a defense mechanism, which enhances both robustness and classification accuracy. This study highlights the limitations of DNA LLMs and underscores the necessity of robustness in bioinformatics.