Universal Adversarial Perturbation Attack on the Inception-Resnet-v1 model and the Effectiveness of Adversarial Retraining as a Suitable Defense Mechanism

In this study, we analyse the impact of the Universal Adversarial Perturbation Attack on the Inception-ResNet-v1 model using the lung CT scan dataset for COVID-19 classification and the retinal OCT scan dataset for Diabetic Macular Edema (DME) classification. The effectiveness of adversarial retraining as a suitable defense mechanism against this attack is examined. This study is categorised into three sections-The implementation of the Inception-ResNet-v1 model, the effect of the attack and the adversarial retraining. © 2023 IEEE.

Investigating the Robustness of Deep Neural Network Based COVID-19 Detection Models Against Universal Adversarial Attacks

Corona viruses are a type of virus with a large family which can cause several terrible and devastating infectious diseases like middle east respiratory syndrome and severe acute respiratory syndrome. The first task of the authority is to screen as many people as possible to detect COVID-19 patients which arises the challenge of rapid screening. Although polymerase chain reaction(PCR) tests are primarily used for the COVID-19 test but because of it's high false negative results and need of experts leading to an alternative diagnostic system based on radiological images like chest X-ray. Moreover, computer aided diagnosis systems from radiography images has significantly been advanced during the last decade with promising efficiency which can overcome the need of both time and experts. In this case, machine learning(ML) and deep learning(DL) based screening techniques can provide automated, fast and reliable results. Therefore, many researchers have proposed several deep neural network(DNN) models for rapid screening of COVID-19 using chest X-ray images. Nevertheless, the vulnerability issue DNN models are overlooked or poorly evaluated in the COVID-19 screening. DNN models are remarkably vulnerable to perturbation which is addressed universal adversarial perturbation (UAP). UAP can falsely influence a DNN model and can eventually lead to going wrong in most of the classification problems. Here, we experimented and evaluated the performance of several DNN based automated COVID-19 diagnostic models, and investigated the robustness of these models against two types of adversarial attack:non targeted and targeted. We showed that DNN based COVID-19 detection models are highly vulnerable to adversarial attack and it is substantially important to be aware of the risk factors of DNN models before deploying for real life applications. © 2021 IEEE.