This paper introduces a tamper-resistant framework for large language models (LLMs) in medical applications, utilizing quantum gradient descent (QGD) to detect malicious parameter modifications in real time. Integrated into a LLaMA-based model, QGD monitors weight amplitude distributions, identifying adversarial fine-tuning anomalies. Tests on the MIMIC and eICU datasets show minimal performance impact (accuracy: 89.1 to 88.3 on MIMIC) while robustly detecting tampering. PubMedQA evaluations confirm preserved biomedical question-answering capabilities. Compared to baselines like selective unlearning and cryptographic fingerprinting, QGD offers superior sensitivity to subtle weight changes. This quantum-inspired approach ensures secure, reliable medical AI, extensible to other high-stakes domains.
@article{arxiv.2506.19086,
title = {Enhancing Biosecurity in Tamper-Resistant Large Language Models With Quantum Gradient Descent},
author = {Fahmida Hai and Saif Nirzhor and Rubayat Khan and Don Roosan},
journal= {arXiv preprint arXiv:2506.19086},
year = {2025}
}
Comments
The conference schedule and details can be found here: https://www.insticc.org/node/technicalprogram/DATA/2025