2008 Second International Conference on Emerging Security Information, Systems and Technologies 2008
DOI: 10.1109/securware.2008.64
|View full text |Cite
|
Sign up to set email alerts
|

Optimal Trust Network Analysis with Subjective Logic

Abstract: Trust network analysis with subjective logic (TNA-SL)

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
302
0
5

Year Published

2010
2010
2023
2023

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 237 publications
(318 citation statements)
references
References 5 publications
0
302
0
5
Order By: Relevance
“…This makes the derived stereotypes easy to be interpreted by the real users. Similarly to our Stereotype-Sharing Overlay Network, in their work, new trustors can request stereotypes from the experienced ones, and then combine these stereotypes with the target agent's reputation (if any) using subjective logic [15]. Although similar, our approach has several advantages: (1) as a basic trust model, StereoTrust uses the (well adapted) beta distribution to derive stereotypes and trust, thus the resulting decision is easy to be interpreted; (2) The work [7] shares agents' local stereotypes heuristically (e.g., no discussion on how stereotype providers are selected) while StereoTrust offers a more sophisticated sharing mechanism by maintaining a dedicated overlay network for exchanging, combining, and updating stereotypes; (3) StereoTrust is applicable in practice as demonstrated in real-world dataset (Epinions.com) based evaluation (see Section 8) presented in this paper, as well as in other diverse applications and settings in which we have applied stereotype to derive trust [22,25].…”
Section: Related Workmentioning
confidence: 99%
“…This makes the derived stereotypes easy to be interpreted by the real users. Similarly to our Stereotype-Sharing Overlay Network, in their work, new trustors can request stereotypes from the experienced ones, and then combine these stereotypes with the target agent's reputation (if any) using subjective logic [15]. Although similar, our approach has several advantages: (1) as a basic trust model, StereoTrust uses the (well adapted) beta distribution to derive stereotypes and trust, thus the resulting decision is easy to be interpreted; (2) The work [7] shares agents' local stereotypes heuristically (e.g., no discussion on how stereotype providers are selected) while StereoTrust offers a more sophisticated sharing mechanism by maintaining a dedicated overlay network for exchanging, combining, and updating stereotypes; (3) StereoTrust is applicable in practice as demonstrated in real-world dataset (Epinions.com) based evaluation (see Section 8) presented in this paper, as well as in other diverse applications and settings in which we have applied stereotype to derive trust [22,25].…”
Section: Related Workmentioning
confidence: 99%
“…In other words, such systems collect feedback, subjective observations which form the basis for trust value computation [38,40].…”
Section: Degree Of Autonomymentioning
confidence: 99%
“…For example, we might take a value of 0 to indicate that there is no trust between the agents in question and a value of 1 to indicate the fullest possible degree of trust between the agents. Other instantiations of O might contain more structure, such as the tuple of numbers used in subjective logic [45,64,90].…”
Section: Trust Networkmentioning
confidence: 99%