Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Davoust, A.; Rovatsos, M.
Social contracts for non-cooperative games Proceedings Article
In: AIES 2020 - Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 43–49, Association for Computing Machinery, Inc, 2020, ISBN: 978-1-4503-7110-0.
Abstract | Links | BibTeX | Tags: Agent society, Agents, Behavioral research, Ethical aspects, Game theory, Game-theoretic, Moral philosophy, Noncooperative game, Selfish behaviours, Social benefits, Social contract, Social welfare
@inproceedings{davoust_social_2020,
title = {Social contracts for non-cooperative games},
author = {A. Davoust and M. Rovatsos},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85082175399&doi=10.1145%2f3375627.3375829&partnerID=40&md5=972ba2201a1c2450895935dc03ec39b9},
doi = {10.1145/3375627.3375829},
isbn = {978-1-4503-7110-0},
year = {2020},
date = {2020-01-01},
booktitle = {AIES 2020 - Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society},
pages = {43–49},
publisher = {Association for Computing Machinery, Inc},
abstract = {In future agent societies, we might see AI systems engaging in selfish, calculated behavior, furthering their owners' interests instead of socially desirable outcomes. How can we promote morally sound behaviour in such settings, in order to obtain more desirable outcomes? A solution from moral philosophy is the concept of a social contract, a set of rules that people would voluntarily commit to in order to obtain better outcomes than those brought by anarchy. We adapt this concept to a game-theoretic setting, to systematically modify the payoffs of a non-cooperative game, so that agents will rationally pursue socially desirable outcomes. We show that for any game, a suitable social contract can be designed to produce an optimal outcome in terms of social welfare. We then investigate the limitations of applying this approach to alternative moral objectives, and establish that, for any alternative moral objective that is significantly different from social welfare, there are games for which no such social contract will be feasible that produces non-negligible social benefit compared to collective selfish behaviour. © 2020 Copyright held by the owner/author(s).},
keywords = {Agent society, Agents, Behavioral research, Ethical aspects, Game theory, Game-theoretic, Moral philosophy, Noncooperative game, Selfish behaviours, Social benefits, Social contract, Social welfare},
pubstate = {published},
tppubtype = {inproceedings}
}
In future agent societies, we might see AI systems engaging in selfish, calculated behavior, furthering their owners' interests instead of socially desirable outcomes. How can we promote morally sound behaviour in such settings, in order to obtain more desirable outcomes? A solution from moral philosophy is the concept of a social contract, a set of rules that people would voluntarily commit to in order to obtain better outcomes than those brought by anarchy. We adapt this concept to a game-theoretic setting, to systematically modify the payoffs of a non-cooperative game, so that agents will rationally pursue socially desirable outcomes. We show that for any game, a suitable social contract can be designed to produce an optimal outcome in terms of social welfare. We then investigate the limitations of applying this approach to alternative moral objectives, and establish that, for any alternative moral objective that is significantly different from social welfare, there are games for which no such social contract will be feasible that produces non-negligible social benefit compared to collective selfish behaviour. © 2020 Copyright held by the owner/author(s).
2.
Davoust, A.; Esfandiari, B.
User participation and honesty in online rating systems: What a social network can do Proceedings Article
In: AAAI Workshop - Technical Report, pp. 477–483, AI Access Foundation, 2016, ISBN: 978-1-57735-759-9.
Abstract | Links | BibTeX | Tags: Aggregation techniques, Artificial intelligence, Behavioral research, Big data, Co-operative behaviors, Cognitive systems, Computer games, Computer programming, Computer systems programming, Data mining, Hybrid systems, Incentive structure, On-line communities, Online rating systems, Online systems, Population statistics, Prisoners' Dilemma, Rating, Social networking (online), User participation
@inproceedings{davoust_user_2016,
title = {User participation and honesty in online rating systems: What a social network can do},
author = {A. Davoust and B. Esfandiari},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021919921&partnerID=40&md5=6a33a1ab6d3b6ddd037240f4f664b6fe},
isbn = {978-1-57735-759-9},
year = {2016},
date = {2016-01-01},
booktitle = {AAAI Workshop - Technical Report},
volume = {WS-16-01 - WS-16-15},
pages = {477–483},
publisher = {AI Access Foundation},
abstract = {An important problem with online communities in general, and online rating systems in particular, is uncooperative behavior: lack of user participation, dishonest contributions. This may be due to an incentive structure akin to a Prisoners' Dilemma (PD). We show that introducing an explicit social network to PD games fosters cooperative behavior, and use this insight to design a new aggregation technique for online rating systems. Using a dataset of ratings from Yelp, we show that our aggregation technique outperforms Yelp's proprietary filter, as well as baseline techniques from recommender systems. Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org).},
keywords = {Aggregation techniques, Artificial intelligence, Behavioral research, Big data, Co-operative behaviors, Cognitive systems, Computer games, Computer programming, Computer systems programming, Data mining, Hybrid systems, Incentive structure, On-line communities, Online rating systems, Online systems, Population statistics, Prisoners' Dilemma, Rating, Social networking (online), User participation},
pubstate = {published},
tppubtype = {inproceedings}
}
An important problem with online communities in general, and online rating systems in particular, is uncooperative behavior: lack of user participation, dishonest contributions. This may be due to an incentive structure akin to a Prisoners' Dilemma (PD). We show that introducing an explicit social network to PD games fosters cooperative behavior, and use this insight to design a new aggregation technique for online rating systems. Using a dataset of ratings from Yelp, we show that our aggregation technique outperforms Yelp's proprietary filter, as well as baseline techniques from recommender systems. Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org).
3.
Chagnon-Forget, M.; Rouhafzay, G.; Cretu, A. -M.; Bouchard, S.
Enhanced Visual-Attention Model for Perceptually Improved 3D Object Modeling in Virtual Environments Journal Article
In: 3D Research, vol. 7, no. 4, 2016, ISSN: 20926731 (ISSN), (Publisher: 3D Display Research Center).
Abstract | Links | BibTeX | Tags: 3-d modeling, 3D modeling, Behavioral research, Complex networks, Interest points, Level of detail, Mesh simplification, Mesh simplifications, Saliency, Three dimensional computer graphics, virtual reality, Visual Attention
@article{chagnon-forget_enhanced_2016,
title = {Enhanced Visual-Attention Model for Perceptually Improved 3D Object Modeling in Virtual Environments},
author = {M. Chagnon-Forget and G. Rouhafzay and A. -M. Cretu and S. Bouchard},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84991727567&doi=10.1007%2fs13319-016-0106-7&partnerID=40&md5=136feba48a1aa3ff798619f8d734c956},
doi = {10.1007/s13319-016-0106-7},
issn = {20926731 (ISSN)},
year = {2016},
date = {2016-01-01},
journal = {3D Research},
volume = {7},
number = {4},
abstract = {Three-dimensional object modeling and interactive virtual environment applications require accurate, but compact object models that ensure real-time rendering capabilities. In this context, the paper proposes a 3D modeling framework employing visual attention characteristics in order to obtain compact models that are more adapted to human visual capabilities. An enhanced computational visual attention model with additional saliency channels, such as curvature, symmetry, contrast and entropy, is initially employed to detect points of interest over the surface of a 3D object. The impact of the use of these supplementary channels is experimentally evaluated. The regions identified as salient by the visual attention model are preserved in a selectively-simplified model obtained using an adapted version of the QSlim algorithm. The resulting model is characterized by a higher density of points in the salient regions, therefore ensuring a higher perceived quality, while at the same time ensuring a less complex and more compact representation for the object. The quality of the resulting models is compared with the performance of other interest point detectors incorporated in a similar manner in the simplification algorithm. The proposed solution results overall in higher quality models, especially at lower resolutions. As an example of application, the selectively-densified models are included in a continuous multiple level of detail (LOD) modeling framework, in which an original neural-network solution selects the appropriate size and resolution of an object. © 2016, 3D Research Center, Kwangwoon University and Springer-Verlag Berlin Heidelberg.},
note = {Publisher: 3D Display Research Center},
keywords = {3-d modeling, 3D modeling, Behavioral research, Complex networks, Interest points, Level of detail, Mesh simplification, Mesh simplifications, Saliency, Three dimensional computer graphics, virtual reality, Visual Attention},
pubstate = {published},
tppubtype = {article}
}
Three-dimensional object modeling and interactive virtual environment applications require accurate, but compact object models that ensure real-time rendering capabilities. In this context, the paper proposes a 3D modeling framework employing visual attention characteristics in order to obtain compact models that are more adapted to human visual capabilities. An enhanced computational visual attention model with additional saliency channels, such as curvature, symmetry, contrast and entropy, is initially employed to detect points of interest over the surface of a 3D object. The impact of the use of these supplementary channels is experimentally evaluated. The regions identified as salient by the visual attention model are preserved in a selectively-simplified model obtained using an adapted version of the QSlim algorithm. The resulting model is characterized by a higher density of points in the salient regions, therefore ensuring a higher perceived quality, while at the same time ensuring a less complex and more compact representation for the object. The quality of the resulting models is compared with the performance of other interest point detectors incorporated in a similar manner in the simplification algorithm. The proposed solution results overall in higher quality models, especially at lower resolutions. As an example of application, the selectively-densified models are included in a continuous multiple level of detail (LOD) modeling framework, in which an original neural-network solution selects the appropriate size and resolution of an object. © 2016, 3D Research Center, Kwangwoon University and Springer-Verlag Berlin Heidelberg.