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

arXiv: https://arxiv.org/abs/2510.24976 · HTML: https://mlsanity.com/paper/2510.24976/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips](https://mlsanity.com/paper/2003.13746/) (2020)
- [Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging](https://mlsanity.com/paper/2401.02565/) (2024)
- [Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare](https://mlsanity.com/paper/2410.01813/) (2024)
- [Adaptive-Gravity: A Defense Against Adversarial Samples](https://mlsanity.com/paper/2204.03694/) (2022)
- [MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption](https://mlsanity.com/paper/2401.09604/) (2024)

## Built on by (most cited first, 1 of 1)

- [Is Mamba Reliable for Medical Imaging?](https://mlsanity.com/paper/2602.16723/) (2026)

## Abstract (arXiv)

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.