Скачать презентацию Intelligent and Adaptive Systems Group Seminar 28 th Скачать презентацию Intelligent and Adaptive Systems Group Seminar 28 th

1974cac4e64df1e1eb01ccd101441786.ppt

  • Количество слайдов: 18

Intelligent and Adaptive Systems Group Seminar 28 th September 2006 Intelligent and Adaptive Systems Group Seminar 28 th September 2006

2 Aim of research • Reduce the uncertainty of agent interactions caused by: – 2 Aim of research • Reduce the uncertainty of agent interactions caused by: – poor performance: substandard quality and tendency for agents to change goals – competition: unreliability of agents due to informationhiding – malicious behaviour: deliberate harm caused by agents through lying and collusion

3 Trust and other notions • Existing research in trust has mostly looked at 3 Trust and other notions • Existing research in trust has mostly looked at the positive side of trust and at the two faces of trustworthiness: trust and no trust • Negative trust is a motivational force (Marsh, 2005) • Untrust: measure of how little an agent is positively trusted [Marsh, S. and Dibben, M. , Trust, untrust, distrust and mistrust – an exploration of the dark(er) side, i. Trust 2005, LNCS 3477, 2005 ]

4 Trust and other notions • Distrust: measure of how much an agent believes 4 Trust and other notions • Distrust: measure of how much an agent believes another agent will actively work against its interests • Undistrust (Griffiths, 2005): lies between distrust and untrust and meaning that an agent is not completely distrusted but still had negative trustworthiness [Griffiths, N. , Enhancing peer-to-peer collaboration using trust, International Journal of Expert Systems with Applications (to appear), 2006]

5 Trust: experience-based • It is directly relevant to the requesting agent • Issues: 5 Trust: experience-based • It is directly relevant to the requesting agent • Issues: – low number of previous interactions or no previous interaction – previous interactions not completely relevant due to differing services and conditions – dishonest behaviour by target agent

6 Trust: recommendation-based • The opinions of third party agents can be requested, directly 6 Trust: recommendation-based • The opinions of third party agents can be requested, directly or indirectly • Recommendations resolve some of the issues linked with direct interactions • Issues: – Inaccurate reporting – Decrease in the reliability with increase in length of the recommendation chain

7 Trust: multi-dimensional • More accurately represent the different aspects of trust • Examples 7 Trust: multi-dimensional • More accurately represent the different aspects of trust • Examples are the dimensions of success, cost, timeliness, quality (Griffiths, 2005) • Other dimensions are competence, disposition, dependence, fulfilment (Castelfranchi, 1998) [Griffiths, N. , Task delegation using experience-based multi-dimensional trust. AAMAS 2005, 2005] [Castelfranchi, C. and Falcone, R. , Principles of trust in MAS: Cognitive anatomy, social importance, and quantification, ICMAS 1998, 1998]

8 Trust: confidence • It is a measure of how accurate a piece of 8 Trust: confidence • It is a measure of how accurate a piece of information is thought to be • Associated with both experience-based and recommendationbased trust • For instance, the more interactions an agent has with a target agent, the higher the confidence in its trust in that agent

9 Trust: reputation • It is the overall opinion of a set of agents 9 Trust: reputation • It is the overall opinion of a set of agents about the trustworthiness of a target agent • The overall opinion is formed from the combined recommendations requested and is affected by who is requesting the information • Compared to e. Bay, the reputation is not unique and accessible to all members of the system

01 Social relationships • Relationships are mainly formed when agents interact with other agents 01 Social relationships • Relationships are mainly formed when agents interact with other agents • The identification of relationships among agents can help to reduce the uncertainty of interactions • Types of relationships: – Underlying affiliation – Group of agents likely to cooperate – Competitors – Collusive behaviour among a group of agents

11 Social relationships: illustration 11 Social relationships: illustration

Trust Model: challenges • Our trust model would have all the necessary features to Trust Model: challenges • Our trust model would have all the necessary features to enable agents to: – assess the trustworthiness of potential interaction partners from past experience – combine past experience with third-party recommendations to obtain the reputation of other agents – identify and use social relationships among agents to better understand agent motivations and behaviour while providing services and information – accurately update the trustworthiness information of agents to reflect changes 21

Trust Model: challenge illustration I • Improve the decision-making of requesting agents faced with Trust Model: challenge illustration I • Improve the decision-making of requesting agents faced with the agents with poor performance • Scenario: – Agent x needs to buy car parts and these are supplied by agents t 1 and t 2 – Agent x has had previous interactions with both • Usage: – Agent x uses its experience-based trust in agent t 1 to assess whether to rely on t 1 – Agent x untrusts t 1 and thus needs to assess t 2's trustworthiness 31

Trust Model: challenge illustration II • Improve the identification by requesting agents of lower Trust Model: challenge illustration II • Improve the identification by requesting agents of lower performing agents which are highly recommended • Scenario: – Agent x needs to buy car parts, supplied by agent t 1 – Agent x has had no previous interactions with t 1 • Usage: – Agent x uses its recommendation-based trust in agent r 1 to ask for its opinion about t 1; r 1 returns a high trust in t 1 – Publicly available information reveal that r 1 and t 1 are owned by the same company – Agent x can use this information to adjust its trust in t 1 41

Trust Model: challenge illustration III • Improve the identification by requesting agents of collusive Trust Model: challenge illustration III • Improve the identification by requesting agents of collusive agents which may defame a target agent • Scenario: – Agent x needs to buy car parts, supplied by agent t 1 – Agent x has had no previous interactions with t 1 • Usage: – Agent x assesses the reputation of t 1 by asking agents r 1, r 2 and r 3 to give their opinions about t 1 – Agents r 1, r 2 and r 3 collude to all give a high distrust recommendation for t 1, which is worse than t 1's real worth – Relationships identifying the recommenders as competitors of t 1 would help x to be aware of the collusion possibility 51

Trust Model: challenge illustration IV • Comparison between potential interaction partners from the trust Trust Model: challenge illustration IV • Comparison between potential interaction partners from the trust values from past experience and from recommendations • Scenario: – Agent x wants to assess the trustworthiness of agents t 1 and t 2 for the next urgent order of car parts – Agent x has interacted once with t 1 and has a very high trust in t 1 in all dimensions – Agent x has interacted 10 times with t 2 and has a low trust in t 2 for its timeliness of delivery 61

Trust Model: challenge illustration IV • Usage: – Using confidence to measure reliability of Trust Model: challenge illustration IV • Usage: – Using confidence to measure reliability of trust value, x can use the higher number of interactions with t 2 as an indication of its higher reliability – By assessing trust dimensions separately, agent x can make the decision to rely on t 2 Usage: – Using confidence to measure reliability of trust value, and assessing trust dimensions separately, x can make the decision to rely on t 2 is not as trustworthy in terms of delivery as t 1, but combining this with the above information, t 2 can be seen to be the less risky choice 71

Trust Model: early design stage • Trust representation • Reputation evaluation • Information gathering Trust Model: early design stage • Trust representation • Reputation evaluation • Information gathering and analysis about underlying affiliations among agents 81