Trusted Decentralized Federated Learning

Gholami, Anousheh; Torkzaban, Nariman; Baras, John S.

doi:10.1109/ccnc49033.2022.9700624

Cited by 17 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A decentralized FL approach avoids having a single-point-of-failure and relies on the agents to implement consensus techniques by exchanging local model updates. Such P2P architectures have recently been proposed [19], [25], [74].…”

Section: Discussion and Extensionsmentioning

confidence: 99%

CELEST: Federated Learning for Globally Coordinated Threat Detection

Ongun¹,

Boboila²,

Oprea³

et al. 2022

Preprint

View full text Add to dashboard Cite

The cyber-threat landscape has evolved tremendously in recent years, with new threat variants emerging daily, and large-scale coordinated campaigns becoming more prevalent. In this study, we propose CELEST (CollaborativE LEarning for Scalable Threat detection), a federated machine learning framework for global threat detection over HTTP, which is one of the most commonly used protocols for malware dissemination and communication. CELEST leverages federated learning in order to collaboratively train a global model across multiple clients who keep their data locally, thus providing increased privacy and confidentiality assurances. Through a novel active learning component integrated with the federated learning technique, our system continuously discovers and learns the behavior of new, evolving, and globally-coordinated cyber threats. We show that CELEST is able to expose attacks that are largely invisible to individual organizations. For instance, in one challenging attack scenario with data exfiltration malware, the global model achieves a three-fold increase in Precision-Recall AUC compared to the local model. We deploy CELEST on two university networks and show that it is able to detect the malicious HTTP communication with high precision and low false positive rates. Furthermore, during its deployment, CELEST detected a set of previously unknown 42 malicious URLs and 20 malicious domains in one day, which were confirmed to be malicious by VirusTotal.

show abstract

Section: Discussion and Extensionsmentioning

confidence: 99%

CELEST: Federated Learning for Globally Coordinated Threat Detection

Ongun¹,

Boboila²,

Oprea³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In some reputation calculation methods for users of a federated learning system, the reputation value of a user is calculated based on the extent to which its local model contributes to the global model [2,[22][23][24]. Gholami et al proposed a trust evaluation scheme for users involved in federated learning to enhance the security of the federated learning [25]. In their scheme, the factor that determines the trust value of a user is the number of times up to now that the user's behavior has been benign and malicious.…”

Section: B Trust Evaluation Schemes For Federated Learningmentioning

confidence: 99%

TFL-DT: A Trust Evaluation Scheme for Federated Learning in Digital Twin for Mobile Networks

Guo,

Liu,

Tian

et al. 2023

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

Due to the distributed collaboration and privacy protection features, federated learning is a promising technology to perform the model training in virtual twins of Digital Twin for Mobile Networks (DTMN). In order to enhance the reliability of the model, it is always expected that the users involved in federated learning have trustworthy behaviors. Yet, available trust evaluation schemes for federated learning have the problems of considering simplex evaluation factor and using coarse-grained trust calculation method. In this paper, we propose a trust evaluation scheme for federated learning in DTMN, which takes direct trust evidence and recommended trust information into account. A user behavior model is designed based on multiple attributes to depict users' behavior in a fine-grained manner. Furthermore, the trust calculation methods for local trust value and recommended trust value of a user are proposed using the data of user behavior model as trust evidence. Several experiments were conducted to verify the effectiveness of the proposed scheme. The results show that the proposed method is able to evaluate the trust levels of users with different behavior patterns accurately. Moreover, it performs better in resisting attacks from users that alternately execute good and bad behaviors compared with state-of-the-art scheme.

show abstract

“…A clustering-based and distance-based trust evaluation methods are proposed in [31]. The clustering-based method groups FL agents based on their trust scores, while the distance-based method calculates the trust scores based on the similarity of FL agents' behaviors.…”

Section: ) Context-awarenessmentioning

confidence: 99%

“…This authors proposes a trusted decentralized FL algorithm based on the concept of trust as a metric for measuring the trustworthiness of network entities in collaborative multi-agent systems [187]. The proposed method updates trust relations among agents based on evidence of their contributive or noncontributive collaboration towards achieving specific goals.…”

Section: Privacy Preserving Flmentioning

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

Trusted Decentralized Federated Learning

Cited by 17 publications

References 10 publications

CELEST: Federated Learning for Globally Coordinated Threat Detection

CELEST: Federated Learning for Globally Coordinated Threat Detection

TFL-DT: A Trust Evaluation Scheme for Federated Learning in Digital Twin for Mobile Networks

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

Contact Info

Product

Resources

About