Impact of Adversarial Examples on the Efficiency of Interpretation and Use of Information from High-Tech Medical Images

Vatian, Aleksandra; Gusarova, Natalia; Dobrenko, Natalia; Dudorov, Sergey; Nigmatullin, Niyaz; Shalyto, Anatoly; Lobantsev, Artem

doi:10.23919/fruct.2019.8711974

Cited by 15 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, Byra et al [102] created an attack based on how ultrasound images were created. Furthermore, high-tech medical imaging systems create a specific noise on images and the authors of [129], used this noise in order to create the attack. We can easily understand that medical attacks use the peculiarities of medical images to harm or reinforce the models.…”

Section: Discussionmentioning

confidence: 99%

“…The authors propose adversarial data augmentation to decrease the vulnerability of nodule detection against some unexpected noise and underrepresented properties of nodules. Vatian et al [129] presented a very interesting work about the adversarial examples as 'natural' adversarial attacks. They have experimented with CT scans for lung cancer screening [130] and Brain MRI [131] using a CNN structure.…”

Section: Defenses-attack Detectionmentioning

confidence: 99%

“…Some of the above methods use adversarial training [22,117,133,141] or the usage of average pooling [123] instead of max pooling as a defensive tactic, which do not affects the complexity of the models. Moreover, some studies like [26,124,127,129] applied adversarial learning in order to improve the performance of models not only in attacks but in general.…”

Section: Defenses-attack Detectionmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Apostolidis

Papakostas

2021

Electronics

View full text Add to dashboard Cite

In the past years, deep neural networks (DNN) have become popular in many disciplines such as computer vision (CV), natural language processing (NLP), etc. The evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to face numerous challenging problems. One of the most important challenges in the CV area is Medical Image Analysis in which DL models process medical images—such as magnetic resonance imaging (MRI), X-ray, computed tomography (CT), etc.—using convolutional neural networks (CNN) for diagnosis or detection of several diseases. The proper function of these models can significantly upgrade the health systems. However, recent studies have shown that CNN models are vulnerable under adversarial attacks with imperceptible perturbations. In this paper, we summarize existing methods for adversarial attacks, detections and defenses on medical imaging. Finally, we show that many attacks, which are undetectable by the human eye, can degrade the performance of the models, significantly. Nevertheless, some effective defense and attack detection methods keep the models safe to an extent. We end with a discussion on the current state-of-the-art and future challenges.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Defenses-attack Detectionmentioning

confidence: 99%

Section: Defenses-attack Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Apostolidis

Papakostas

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…In the past, adversarial training on medical DL models have shown mixed results. In some studies, adversarial training improved DL model robustness for multiple medical imaging modalities like lung CT and retinal optical coherence tomography (37,39,40). On the other hand, Hirano et al found that adversarial training generally did not increase model robustness for classifying dermatoscopic images, optical coherence tomography images, and chest X-ray images (41).…”

Section: Discussionmentioning

confidence: 99%

Using Adversarial Images to Assess the Stability of Deep Learning Models Trained on Diagnostic Images in Oncology

Joel

Umrao

Chang

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundDeep learning (DL) models have shown the ability to automate the classification of medical images used for cancer detection. Unfortunately, recent studies have found that DL models are vulnerable to adversarial attacks which manipulate models into making incorrect predictions with high confidence. There is a need for better understanding of how adversarial attacks impact the predictive ability of DL models in the medical image domain.MethodsWe studied the adversarial attack susceptibility of DL models for three common imaging tasks within oncology. We investigated how PGD adversarial training could be employed to increase model robustness against FGSM, PGD, and BIM attacks. Finally, we studied the utility of adversarial sensitivity as a metric to improve model performance.ResultsOur experiments showed that medical DL models were highly sensitive to adversarial attacks, as visually imperceptible degrees of perturbation (<0.004) were sufficient to deceive the model the majority of the time. DL models for medical images were more vulnerable to adversarial attacks compared to DL models for non-medical images. Adversarial training increased model performance on adversarial samples for all classification tasks. We were able to increase model accuracy on clean images for all datasets by excluding images most vulnerable to adversarial perturbation.ConclusionOur results indicated that while medical DL systems are extremely susceptible to adversarial attacks, adversarial training show promise as an effective defense against attacks. Adversarial susceptibility of individual images can be used to increase model performance by identifying images most at-risk for misclassification. Our findings provide a useful basis for designing more robust and accurate medical DL models as well as techniques to defend models from adversarial attack.

show abstract

“…Adversarial examples have received much attention in image and text-domain, yet very few work has been done on Electronic Health Records (EHR). Most existing works on adversarial examples in medical domains have been focused on medical images (Vatian et al, 2019;Ma et al, 2020). A few works have studied adversarial examples in numerical EHR data (Sun et al, 2018;.…”

Section: Introductionmentioning

confidence: 99%

Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries

Wang

Park

Lee

et al. 2020

Proceedings of the 3rd Clinical Natural Language Processing Workshop

View full text Add to dashboard Cite

Recent studies have shown that adversarial examples can be generated by applying small perturbations to the inputs such that the welltrained deep learning models will misclassify. With the increasing number of safety and security-sensitive applications of deep learning models, the robustness of deep learning models has become a crucial topic. The robustness of deep learning models for healthcare applications is especially critical because the unique characteristics and the high financial interests of the medical domain make it more sensitive to adversarial attacks. Among the modalities of medical data, the clinical summaries have higher risks to be attacked because they are generated by third-party companies. As few works studied adversarial threats on clinical summaries, in this work we first apply adversarial attack to clinical summaries of electronic health records (EHR) to show the text-based deep learning systems are vulnerable to adversarial examples. Secondly, benefiting from the multi-modality of the EHR dataset, we propose a novel defense method, MATCH (Multimodal feATure Consistency cHeck), which leverages the consistency between multiple modalities in the data to defend against adversarial examples on a single modality. Our experiments demonstrate the effectiveness of MATCH on a hospital readmission prediction task comparing with baseline methods.

show abstract

Impact of Adversarial Examples on the Efficiency of Interpretation and Use of Information from High-Tech Medical Images

Cited by 15 publications

References 15 publications

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

A Survey on Adversarial Deep Learning Robustness in Medical Image Analysis

Using Adversarial Images to Assess the Stability of Deep Learning Models Trained on Diagnostic Images in Oncology

Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries

Contact Info

Product

Resources

About