Agent EXPRI: Licence to Explain

Francesca Mosca; Stefan Sarkadi; Jose M Such; Peter McBurney

Agent EXPRI: Licence to Explain

Francesca Mosca, Stefan Sarkadi, Jose M Such, Peter McBurney

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

69 Downloads (Pure)

Abstract

Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.

Original language	English
Title of host publication	2nd International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems
Publication status	Accepted/In press - 2020

Keywords

Privacy
Explainable Agents
Practical Reasoning

Access to Document

extraamas2020_cr

Cite this

@inbook{689a488faa9c4e6cbcc09243ea728816,

title = "Agent EXPRI: Licence to Explain",

abstract = "Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.",

keywords = "Privacy, Explainable Agents, Practical Reasoning",

author = "Francesca Mosca and Stefan Sarkadi and Such, {Jose M} and Peter McBurney",

year = "2020",

language = "English",

booktitle = "2nd International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems",

}

TY - CHAP

T1 - Agent EXPRI: Licence to Explain

AU - Mosca, Francesca

AU - Sarkadi, Stefan

AU - Such, Jose M

AU - McBurney, Peter

PY - 2020

Y1 - 2020

N2 - Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.

AB - Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.

KW - Privacy

KW - Explainable Agents

KW - Practical Reasoning

M3 - Conference paper

BT - 2nd International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems

ER -

Agent EXPRI: Licence to Explain

Abstract

Keywords

Access to Document

Fingerprint

Cite this