Probing Adversarial Robustness of Protein Language Models: A Reproducible Case Study of ESM-2 Under Substitution-Based Attacks

Date

Authors

Niloy, Md. Robiul Islam

Moazzam, Md. Golam

Publisher

AIUB Office of Research and Publication

Impulse

Average

Influence

Average

Popularity

Average

Keywords

Deep Learning, ESM-2, Bayesian Uncertainty, Biosecurity, Pseudo-perplexity, Protein Language Models (PLMs), Machine Learning Security, Adversarial Robustness, Substitution-Based Attacks, Knowledge Distillation, Dual-Use Research, AI Governance

Scopus Q

OpenCitations Citation Count

N/A

Source

AIUB Journal of Science and Engineering

Volume

24

Issue

2

Start Page

141

End Page

149

URI

https://hdl.handle.net/20.500.12573/6037
https://doi.org/10.53799/gteskx50

Collections

Scopus İndeksli Yayınlar Koleksiyonu

Google Scholar™

OpenAlex FWCI

0.00

Sustainable Development Goals