Federated Trustworthy AI Architecture for Smart Cities

Utomo, Sapdo; John, A; Rouniyar, Adarsh; Hsu, Hsiu-Chun; Hsiung, Pao-Ann

doi:10.1109/isc255366.2022.9922069

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The foundational principle of FL revolves around maintaining data on the client side, as discussed earlier, aiming to fortify system security and privacy. In our prior research [40], we introduced a federated trustworthy AI (FTAI) architecture tailored to meet seven key requirements of trustworthy AI (TAI) outlined by the European Union [41]. Specifically, in this paper, the proposed method delves into TAI requirements two and three, focusing on robustness, safety, privacy, and data governance.…”

Section: Related Workmentioning

confidence: 99%

Federated Adversarial Training Strategies for Achieving Privacy and Security in Sustainable Smart City Applications

Utomo,

Rouniyar,

Hsu

et al. 2023

Future Internet

Self Cite

View full text Add to dashboard Cite

Smart city applications that request sensitive user information necessitate a comprehensive data privacy solution. Federated learning (FL), also known as privacy by design, is a new paradigm in machine learning (ML). However, FL models are susceptible to adversarial attacks, similar to other AI models. In this paper, we propose federated adversarial training (FAT) strategies to generate robust global models that are resistant to adversarial attacks. We apply two adversarial attack methods, projected gradient descent (PGD) and the fast gradient sign method (FGSM), to our air pollution dataset to generate adversarial samples. We then evaluate the effectiveness of our FAT strategies in defending against these attacks. Our experiments show that FGSM-based adversarial attacks have a negligible impact on the accuracy of global models, while PGD-based attacks are more effective. However, we also show that our FAT strategies can make global models robust enough to withstand even PGD-based attacks. For example, the accuracy of our FAT-PGD and FL-mixed-PGD models is 81.13% and 82.60%, respectively, compared to 91.34% for the baseline FL model. This represents a reduction in accuracy of 10%, but this could be potentially mitigated by using a more complex and larger model. Our results demonstrate that FAT can enhance the security and privacy of sustainable smart city applications. We also show that it is possible to train robust global models from modest datasets per client, which challenges the conventional wisdom that adversarial training requires massive datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Federated Adversarial Training Strategies for Achieving Privacy and Security in Sustainable Smart City Applications

Utomo,

Rouniyar,

Hsu

et al. 2023

Future Internet

Self Cite

View full text Add to dashboard Cite

show abstract

“…Authors in [55] introduces the Federated Trustworthy Artificial Intelligence (FTAI) Architecture, which combines TAI Architecture and FL to provide a secure platform for user data privacy. The proposed model aggregation strategy integrates FedCS and FedPSO, and employs AIF360 to guarantee fairness in the client-side training process by eliminating discrimination.…”

Section: Trustworthy Model Selectionmentioning

confidence: 99%

Common misconceptions regarding COVID-19 among health care professionals: an online global cross-sectional survey

Tariq¹,

Hamid²,

Mashood³

et al. 2020

J Oral Res

View full text Add to dashboard Cite

Background: The COVID-19 pandemic has taken the world by storm, with cases continuously increasing by the hour and with a shortage of information regarding the virus available to the general public. Despite the availability of trusted online sources, there are still misconceptions relating to the virus floating around. This study aimed to find out the level of misconceptions among healthcare professionals (HCPs) worldwide about the ensuing COVID-19 pandemic. Materials and Methods: A descriptive cross sectional study was conducted through a global online survey. The self-administered questionnaire was designed and registered at an online website (Kwiksurveys). A total of 652 participants from 35 different countries across the world responded. Statistical analysis was performed using SPSS version 23. Socio-demographic and discipline characteristics were compared with the help of the chi-square test and univariate and multivariate logistic regression to find significant relationships. Results: Among all HCPs, general physicians (61.2%) were the most common respondents. The responses from females (63.3%) almost doubled those of men, and nearly half of the participants were working in private institutes (49.2%). Additionally, the major source of information used by HCPs about COVID-19 was social media (55.4%). Regarding misconception assessment, 71.6% of participants had correct concepts regarding COVID-19. However, 28.4% had incorrect information. Female HCPs were 1.49 times more likely to have correct concepts compared to males (OR=1.49, 95% CI=1.04-2.14). Conclusions: The majority of the HCPs were keeping themselves up-to-date with current information concerning the knowledge, prevention, and hygiene practices of COVID-19 infection. However, some misconceptions are deeply rooted in the mindsets of HCPs worldwide and need to be addressed by the continuous professional development of HCPs. The availability of reliable sources of information on the pandemic should be encouraged, with adequate explanations also available to the general public in simple terms.

show abstract

“…Using XAI is meant to make it easier to comprehend and diagnose model output, regardless of how accurate the output may be. In conclusion, it will help the user comprehend the results of the system and provide the model's developer insightful input for bettering the model [11,12]. In one study, the diabetes classification framework based on the XAI method was interpreted and designed by taking into account the results obtained from the Shapley method in the explanations of the model [13].…”

Section: Introductionmentioning

confidence: 99%

Explainable Artificial Intelligence Paves the Way in Precision Diagnostics and Biomarker Discovery for the Subclass of Diabetic Retinopathy in Type 2 Diabetics

Yagin,

Yasar,

Gormez

et al. 2023

Metabolites

View full text Add to dashboard Cite

Diabetic retinopathy (DR), a common ocular microvascular complication of diabetes, contributes significantly to diabetes-related vision loss. This study addresses the imperative need for early diagnosis of DR and precise treatment strategies based on the explainable artificial intelligence (XAI) framework. The study integrated clinical, biochemical, and metabolomic biomarkers associated with the following classes: non-DR (NDR), non-proliferative diabetic retinopathy (NPDR), and proliferative diabetic retinopathy (PDR) in type 2 diabetes (T2D) patients. To create machine learning (ML) models, 10% of the data was divided into validation sets and 90% into discovery sets. The validation dataset was used for hyperparameter optimization and feature selection stages, while the discovery dataset was used to measure the performance of the models. A 10-fold cross-validation technique was used to evaluate the performance of ML models. Biomarker discovery was performed using minimum redundancy maximum relevance (mRMR), Boruta, and explainable boosting machine (EBM). The predictive proposed framework compares the results of eXtreme Gradient Boosting (XGBoost), natural gradient boosting for probabilistic prediction (NGBoost), and EBM models in determining the DR subclass. The hyperparameters of the models were optimized using Bayesian optimization. Combining EBM feature selection with XGBoost, the optimal model achieved (91.25 ± 1.88) % accuracy, (89.33 ± 1.80) % precision, (91.24 ± 1.67) % recall, (89.37 ± 1.52) % F1-Score, and (97.00 ± 0.25) % the area under the ROC curve (AUROC). According to the EBM explanation, the six most important biomarkers in determining the course of DR were tryptophan (Trp), phosphatidylcholine diacyl C42:2 (PC.aa.C42.2), butyrylcarnitine (C4), tyrosine (Tyr), hexadecanoyl carnitine (C16) and total dimethylarginine (DMA). The identified biomarkers may provide a better understanding of the progression of DR, paving the way for more precise and cost-effective diagnostic and treatment strategies.

show abstract

Federated Trustworthy AI Architecture for Smart Cities

Cited by 3 publications

References 0 publications

Federated Adversarial Training Strategies for Achieving Privacy and Security in Sustainable Smart City Applications

Federated Adversarial Training Strategies for Achieving Privacy and Security in Sustainable Smart City Applications

Common misconceptions regarding COVID-19 among health care professionals: an online global cross-sectional survey

Explainable Artificial Intelligence Paves the Way in Precision Diagnostics and Biomarker Discovery for the Subclass of Diabetic Retinopathy in Type 2 Diabetics

Contact Info

Product

Resources

About