Wavelet-based adversarial training: Cybersecurity system protects medical digital twins from attacks

Wavelet-based adversarial training: Cybersecurity system protects medical digital twins from attacks

A digital twin is an exact virtual copy of a real-world system. Built using real-time data, they provide a platform to test, simulate, and optimize the performance of their physical counterpart. In health care, medical digital twins can create virtual models of biological systems to predict diseases or test medical treatments. However, medical digital twins are susceptible to adversarial attacks, where small, intentional modifications to input d…

Defense system protects medical digital twins from cyberattack

A new method enables medical digital twins to achieve 98% accuracy in breast cancer prediction, even under adversarial attacks

Dongguk University Researchers Develop Wavelet-Based Adversarial Training: A Defense System for Medical Digital Twins

Insider Brief Researchers developed a new defense system, Wavelet-Based Adversarial Training (WBAD), to protect medical digital twins from cyberattacks. WBAD combines wavelet denoising with adversarial training to restore diagnostic accuracy after attacks that can manipulate input data and cause false predictions. Tested on a breast cancer digital twin, the system improved accuracy from 5% to 98% against common adversarial attacks, according …