Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation

Ozbulak, Utku; Messem, Arnout Van; Neve, Wesley De

doi:10.48550/arxiv.1907.13124

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ozbulak et al [41] demonstrated that deep-learning-based medical image segmentation models are susceptible to AAs. They concentrated on optic disc segmentation in glaucoma and targeted attacks.…”

Section: Adaptive Segmentation Mask Attackmentioning

confidence: 99%

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

Zbrzezny

Grzybowski²

2023

JCM

View full text Add to dashboard Cite

The artificial intelligence (AI) systems used for diagnosing ophthalmic diseases have significantly progressed in recent years. The diagnosis of difficult eye conditions, such as cataracts, diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity, has become significantly less complicated as a result of the development of AI algorithms, which are currently on par with ophthalmologists in terms of their level of effectiveness. However, in the context of building AI systems for medical applications such as identifying eye diseases, addressing the challenges of safety and trustworthiness is paramount, including the emerging threat of adversarial attacks. Research has increasingly focused on understanding and mitigating these attacks, with numerous articles discussing this topic in recent years. As a starting point for our discussion, we used the paper by Ma et al. “Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems”. A literature review was performed for this study, which included a thorough search of open-access research papers using online sources (PubMed and Google). The research provides examples of unique attack strategies for medical images. Unfortunately, unique algorithms for attacks on the various ophthalmic image types have yet to be developed. It is a task that needs to be performed. As a result, it is necessary to build algorithms that validate the computation and explain the findings of artificial intelligence models. In this article, we focus on adversarial attacks, one of the most well-known attack methods, which provide evidence (i.e., adversarial examples) of the lack of resilience of decision models that do not include provable guarantees. Adversarial attacks have the potential to provide inaccurate findings in deep learning systems and can have catastrophic effects in the healthcare industry, such as healthcare financing fraud and wrong diagnosis.

show abstract

Section: Adaptive Segmentation Mask Attackmentioning

confidence: 99%

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

Zbrzezny

Grzybowski²

2023

JCM

View full text Add to dashboard Cite

show abstract

“…In some cases, the performance of the model decreased by 100% [ 19 ]. Ozbulak et al [ 20 ] proposed a targeted attack for medical image segmentation, which is named Adaptive Segmentation Mask Attack (ASMA). This attack creates imperceptible samples and achieves high Intersection-over-Union (IoU) degradation.…”

Section: Related Workmentioning

confidence: 99%

Digital Watermarking as an Adversarial Attack on Medical Image Analysis with Deep Learning

Apostolidis

Papakostas

2022

J. Imaging

View full text Add to dashboard Cite

In the past years, Deep Neural Networks (DNNs) have become popular in many disciplines such as Computer Vision (CV), and the evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to deal with several problems. One of the most important challenges in the CV area is Medical Image Analysis. However, adversarial attacks have proven to be an important threat to vision systems by significantly reducing the performance of the models. This paper brings to light a different side of digital watermarking, as a potential black-box adversarial attack. In this context, apart from proposing a new category of adversarial attacks named watermarking attacks, we highlighted a significant problem, as the massive use of watermarks, for security reasons, seems to pose significant risks to vision systems. For this purpose, a moment-based local image watermarking method is implemented on three modalities, Magnetic Resonance Images (MRI), Computed Tomography (CT-scans), and X-ray images. The introduced methodology was tested on three state-of-the art CV models, DenseNet 201, DenseNet169, and MobileNetV2. The results revealed that the proposed attack achieved over 50% degradation of the model’s performance in terms of accuracy. Additionally, MobileNetV2 was the most vulnerable model and the modality with the biggest reduction was CT-scans.

show abstract

“…This attack was tested on the InceptionResNetV2 model. The authors in [ 25 ] created an attack for segmentation on fundoscopy and dermoscopy images, using the U-Net model. In addition, [ 26 ] developed an attack for fundoscopy images, which can be implemented on segmentation and classification tasks.…”

Section: Introductionmentioning

confidence: 99%

How Resilient Are Deep Learning Models in Medical Image Analysis? The Case of the Moment-Based Adversarial Attack (Mb-AdA)

2022

View full text Add to dashboard Cite

In the past years, deep neural networks (DNNs) have become popular in many disciplines such as computer vision (CV). One of the most important challenges in the CV area is Medical Image Analysis (MIA). However, adversarial attacks (AdAs) have proven to be an important threat to vision systems by significantly reducing the performance of the models. This paper proposes a new black-box adversarial attack, which is based οn orthogonal image moments named Mb-AdA. Additionally, a corresponding defensive method of adversarial training using Mb-AdA adversarial examples is also investigated, with encouraging results. The proposed attack was applied in classification and segmentation tasks with six state-of-the-art Deep Learning (DL) models in X-ray, histopathology and nuclei cell images. The main advantage of Mb-AdA is that it does not destroy the structure of images like other attacks, as instead of adding noise it removes specific image information, which is critical for medical models’ decisions. The proposed attack is more effective than compared ones and achieved degradation up to 65% and 18% in terms of accuracy and IoU for classification and segmentation tasks, respectively, by also presenting relatively high SSIM. At the same time, it was proved that Mb-AdA adversarial examples can enhance the robustness of the model.

show abstract

Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation

Cited by 3 publications

References 0 publications

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology

Digital Watermarking as an Adversarial Attack on Medical Image Analysis with Deep Learning

How Resilient Are Deep Learning Models in Medical Image Analysis? The Case of the Moment-Based Adversarial Attack (Mb-AdA)

Contact Info

Product

Resources

About