AAAI 2024technical1 citations
Attacking CNNs in Histopathology with SNAP: Sporadic and Naturalistic Adversarial Patches (Student Abstract)
Daya Kumar, Abhijith Sharma, Apurva Narayan
Abstract
Convolutional neural networks (CNNs) are being increasingly adopted in medical imaging. However, in the race for developing accurate models, their robustness is often overlooked. This elicits a significant concern given the safety-critical nature of the healthcare system. Here, we highlight the vulnerability of CNNs against a sporadic and naturalistic adversarial patch attack (SNAP). We train SNAP to mislead the ResNet50 model predicting metastasis in histopathological scans of lymph node sections, lowering the accuracy by 27%. This work emphasizes the need for defense strategies before deploying CNNs in critical healthcare settings.
BibTeX
@article{Kumar_Sharma_Narayan_2024, title={Attacking CNNs in Histopathology with SNAP: Sporadic and Naturalistic Adversarial Patches (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30468}, DOI={10.1609/aaai.v38i21.30468}, abstractNote={Convolutional neural networks (CNNs) are being increasingly
adopted in medical imaging. However, in the race for
developing accurate models, their robustness is often overlooked.
This elicits a significant concern given the safety-critical
nature of the healthcare system. Here, we highlight
the vulnerability of CNNs against a sporadic and naturalistic
adversarial patch attack (SNAP). We train SNAP to mislead
the ResNet50 model predicting metastasis in histopathological
scans of lymph node sections, lowering the accuracy by
27%. This work emphasizes the need for defense strategies
before deploying CNNs in critical healthcare settings.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Kumar, Daya and Sharma, Abhijith and Narayan, Apurva}, year={2024}, month={Mar.}, pages={23550-23551} }