Deep-Learning based Reputation Model for Indirect Trust
Management

D 2023

Deep-Learning based Reputation Model for Indirect Trust Management

BANGUI, Hind; Mouzhi GE a Barbora BÜHNOVÁ

Základní údaje

Originální název

Deep-Learning based Reputation Model for Indirect Trust Management

Autoři

BANGUI, Hind (504 Maroko, garant, domácí); Mouzhi GE (156 Čína) a Barbora BÜHNOVÁ (203 Česká republika, domácí)

Vydání

Neuveden, 14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2023), od s. 405-412, 8 s. 2023

Nakladatel

Elsevier

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Kód RIV

RIV/00216224:14330/23:00130330

Organizační jednotka

Fakulta informatiky

ISSN

DOI

http://dx.doi.org/10.1016/j.procs.2023.03.052

EID Scopus

2-s2.0-85162885481

Klíčová slova anglicky

Trust Management; Deep learning; IoT; AI

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 7. 4. 2024 22:49, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

In the digital era, human and thing behavioral patterns have been merged, which leads to the need for trust management to secure the relationship among people and things (e.g., driverless cars). Due to the dynamism and complexity of digital environments, trust management depends largely on indirect trust to support its reasoning by building the reputation of trustees based on recommendations reflected in the feedback of sentiment and non-sentiment objects. However, different biases are still affecting the accuracy of indirect trust that reflects a collective trustworthiness belief or societal stereotypes. This work focuses on enabling indirect trust management by leveraging deep learning in combination with synthetic data for bias management. Specifically, this paper proposes a reputation model to support decision-making in trust management by minimizing bias in indirect trust information and fostering fairly the relationship among sentiment and non-sentiment objects. Our experimental results show that the synthetic data can significantly improve the classification accuracy in trust management.

Návaznosti

CZ.02.1.01/0.0/0.0/16_019/0000822, interní kód MU
(Kód CEP: EF16_019/0000822)

Název: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur (Akronym: C4e)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur, PO 1 Posilování kapacit pro kvalitní výzkum

EF16_019/0000822, projekt VaV

Název: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur

Citovat

BANGUI, Hind; Mouzhi GE a Barbora BÜHNOVÁ. Deep-Learning based Reputation Model for Indirect Trust Management. Online. In 14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2023). Neuveden: Elsevier, 2023, s. 405-412. ISSN 1877-0509. Dostupné z: https://dx.doi.org/10.1016/j.procs.2023.03.052.

@inproceedings{2255177,
   author = {Bangui, Hind and Ge, Mouzhi and Bühnová, Barbora},
   address = {Neuveden},
   booktitle = {14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2023)},
   doi = {http://dx.doi.org/10.1016/j.procs.2023.03.052},
   keywords = {Trust Management; Deep learning; IoT; AI},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   pages = {405-412},
   publisher = {Elsevier},
   title = {Deep-Learning based Reputation Model for Indirect Trust Management},
   url = {https://doi.org/10.1016/j.procs.2023.03.052},
   year = {2023}
}

TY  - CONF
ID  - 2255177
AU  - Bangui, Hind - Ge, Mouzhi - Bühnová, Barbora
PY  - 2023
TI  - Deep-Learning based Reputation Model for Indirect Trust Management
PB  - Elsevier
CY  - Neuveden
KW  - Trust Management
KW  - Deep learning
KW  - IoT
KW  - AI
UR  - https://doi.org/10.1016/j.procs.2023.03.052
N2  - In the digital era, human and thing behavioral patterns have been merged, which leads to the need for trust management to secure the relationship among people and things (e.g., driverless cars). Due to the dynamism and complexity of digital environments, trust management depends largely on indirect trust to support its reasoning by building the reputation of trustees based on recommendations reflected in the feedback of sentiment and non-sentiment objects. However, different biases are still affecting the accuracy of indirect trust that reflects a collective trustworthiness belief or societal stereotypes. This work focuses on enabling indirect trust management by leveraging deep learning in combination with synthetic data for bias management. Specifically, this paper proposes a reputation model to support decision-making in trust management by minimizing bias in indirect trust information and fostering fairly the relationship among sentiment and non-sentiment objects. Our experimental results show that the synthetic data can significantly improve the classification accuracy in trust management.
ER  -

BANGUI, Hind; Mouzhi GE a Barbora BÜHNOVÁ. Deep-Learning based Reputation Model for Indirect Trust Management. Online. In \textit{14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2023)}. Neuveden: Elsevier, 2023, s.~405-412. ISSN~1877-0509. Dostupné z: https://dx.doi.org/10.1016/j.procs.2023.03.052.

Přehled o publikaci