Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Latibari, Banafsheh Saber, Nazari, Najmeh, Sayadi, Hossein, Homayoun, Houman, Mahalanobis, Abhijit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917049136054272
author Latibari, Banafsheh Saber
Nazari, Najmeh
Sayadi, Hossein
Homayoun, Houman
Mahalanobis, Abhijit
author_facet Latibari, Banafsheh Saber
Nazari, Najmeh
Sayadi, Hossein
Homayoun, Houman
Mahalanobis, Abhijit
contents Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we propose a novel threat model referred to as Med-Hammer that combines the Rowhammer hardware fault injection with neural Trojan attacks to compromise the integrity of ViT-based medical imaging systems. Specifically, we demonstrate how malicious bit flips induced via Rowhammer can trigger implanted neural Trojans, leading to targeted misclassification or suppression of critical diagnoses (e.g., tumors or lesions) in medical scans. Through extensive experiments on benchmark medical imaging datasets such as ISIC, Brain Tumor, and MedMNIST, we show that such attacks can remain stealthy while achieving high attack success rates about 82.51% and 92.56% in MobileViT and SwinTransformer, respectively. We further investigate how architectural properties, such as model sparsity, attention weight distribution, and the number of features of the layer, impact attack effectiveness. Our findings highlight a critical and underexplored intersection between hardware-level faults and deep learning security in healthcare applications, underscoring the urgent need for robust defenses spanning both model architectures and underlying hardware platforms.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24976
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
Latibari, Banafsheh Saber
Nazari, Najmeh
Sayadi, Hossein
Homayoun, Houman
Mahalanobis, Abhijit
Cryptography and Security
Artificial Intelligence
Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we propose a novel threat model referred to as Med-Hammer that combines the Rowhammer hardware fault injection with neural Trojan attacks to compromise the integrity of ViT-based medical imaging systems. Specifically, we demonstrate how malicious bit flips induced via Rowhammer can trigger implanted neural Trojans, leading to targeted misclassification or suppression of critical diagnoses (e.g., tumors or lesions) in medical scans. Through extensive experiments on benchmark medical imaging datasets such as ISIC, Brain Tumor, and MedMNIST, we show that such attacks can remain stealthy while achieving high attack success rates about 82.51% and 92.56% in MobileViT and SwinTransformer, respectively. We further investigate how architectural properties, such as model sparsity, attention weight distribution, and the number of features of the layer, impact attack effectiveness. Our findings highlight a critical and underexplored intersection between hardware-level faults and deep learning security in healthcare applications, underscoring the urgent need for robust defenses spanning both model architectures and underlying hardware platforms.
title Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2510.24976