Exploring Adversarial Robustness in Classification tasks using DNA Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916637520691200 |
|---|---|
| author | Yoo, Hyunwoo Shin, Haebin Xu, Kaidi Rosen, Gail |
| author_facet | Yoo, Hyunwoo Shin, Haebin Xu, Kaidi Rosen, Gail |
| contents | DNA Language Models, 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 language models 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 language models 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 language models and underscores the necessity of robustness in bioinformatics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19788 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Adversarial Robustness in Classification tasks using DNA Language Models Yoo, Hyunwoo Shin, Haebin Xu, Kaidi Rosen, Gail Computation and Language DNA Language Models, 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 language models 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 language models 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 language models and underscores the necessity of robustness in bioinformatics. |
| title | Exploring Adversarial Robustness in Classification tasks using DNA Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.19788 |