FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100894666> ?p ?o ?g. }

• W3100894666 abstract "With the rapid development of artificial intelligence (AI), ethical issues surrounding AI have attracted increasing attention. In particular, autonomous vehicles may face moral dilemmas in accident scenarios, such as staying the course resulting in hurting pedestrians or swerving leading to hurting passengers. To investigate such ethical dilemmas, recent studies have adopted preference aggregation, in which each voter expresses her/his preferences over decisions for the possible ethical dilemma scenarios, and a centralized system aggregates these preferences to obtain the winning decision. Although a useful methodology for building ethical AI systems, such an approach can potentially violate the privacy of voters since moral preferences are sensitive information and their disclosure can be exploited by malicious parties resulting in negative consequences. In this paper, we report a first-of-its-kind privacy-preserving crowd-guided AI decision-making approach in ethical dilemmas. We adopt the formal and popular notion of differential privacy to quantify privacy, and consider four granularities of privacy protection by taking voter-/record-level privacy protection and centralized/distributed perturbation into account, resulting in four approaches VLCP, RLCP, VLDP, and RLDP, respectively. Moreover, we propose different algorithms to achieve these privacy protection granularities, while retaining the accuracy of the learned moral preference model. Specifically, VLCP and RLCP are implemented with the data aggregator setting a universal privacy parameter and perturbing the averaged moral preference to protect the privacy of voters' data. VLDP and RLDP are implemented in such a way that each voter perturbs her/his local moral preference with a personalized privacy parameter. Extensive experiments based on both synthetic data and real-world data of voters' moral decisions demonstrate that the proposed approaches achieve high accuracy of preference aggregation while protecting individual voter's privacy." @default.
• W3100894666 created "2020-11-23" @default.
• W3100894666 creator A5025145213 @default.
• W3100894666 creator A5030613480 @default.
• W3100894666 creator A5056067943 @default.
• W3100894666 creator A5064069283 @default.
• W3100894666 creator A5064348390 @default.
• W3100894666 creator A5071321132 @default.
• W3100894666 creator A5083582213 @default.
• W3100894666 date "2019-11-03" @default.
• W3100894666 modified "2023-10-04" @default.
• W3100894666 title "Privacy-preserving Crowd-guided AI Decision-making in Ethical Dilemmas" @default.
• W3100894666 cites W1557833142 @default.
• W3100894666 cites W1873763122 @default.
• W3100894666 cites W2024622963 @default.
• W3100894666 cites W2051267297 @default.
• W3100894666 cites W2097427281 @default.
• W3100894666 cites W2100960835 @default.
• W3100894666 cites W2113792377 @default.
• W3100894666 cites W2162379889 @default.
• W3100894666 cites W2473418344 @default.
• W3100894666 cites W2756321254 @default.
• W3100894666 cites W2810967793 @default.
• W3100894666 cites W2823329128 @default.
• W3100894666 cites W2903959356 @default.
• W3100894666 cites W2963629772 @default.
• W3100894666 cites W3102407811 @default.
• W3100894666 doi "https://doi.org/10.1145/3357384.3357954" @default.
• W3100894666 hasPublicationYear "2019" @default.
• W3100894666 type Work @default.
• W3100894666 sameAs 3100894666 @default.
• W3100894666 citedByCount "5" @default.
• W3100894666 countsByYear W31008946662020 @default.
• W3100894666 countsByYear W31008946662021 @default.
• W3100894666 crossrefType "proceedings-article" @default.
• W3100894666 hasAuthorship W3100894666A5025145213 @default.
• W3100894666 hasAuthorship W3100894666A5030613480 @default.
• W3100894666 hasAuthorship W3100894666A5056067943 @default.
• W3100894666 hasAuthorship W3100894666A5064069283 @default.
• W3100894666 hasAuthorship W3100894666A5064348390 @default.
• W3100894666 hasAuthorship W3100894666A5071321132 @default.
• W3100894666 hasAuthorship W3100894666A5083582213 @default.
• W3100894666 hasBestOaLocation W31008946662 @default.
• W3100894666 hasConcept C108827166 @default.
• W3100894666 hasConcept C123201435 @default.
• W3100894666 hasConcept C124101348 @default.
• W3100894666 hasConcept C15744967 @default.
• W3100894666 hasConcept C162324750 @default.
• W3100894666 hasConcept C175444787 @default.
• W3100894666 hasConcept C17744445 @default.
• W3100894666 hasConcept C193934123 @default.
• W3100894666 hasConcept C199539241 @default.
• W3100894666 hasConcept C23130292 @default.
• W3100894666 hasConcept C2524010 @default.
• W3100894666 hasConcept C2776768071 @default.
• W3100894666 hasConcept C2778496695 @default.
• W3100894666 hasConcept C2781249084 @default.
• W3100894666 hasConcept C2994541713 @default.
• W3100894666 hasConcept C3017597292 @default.
• W3100894666 hasConcept C33923547 @default.
• W3100894666 hasConcept C38652104 @default.
• W3100894666 hasConcept C41008148 @default.
• W3100894666 hasConcept C77805123 @default.
• W3100894666 hasConceptScore W3100894666C108827166 @default.
• W3100894666 hasConceptScore W3100894666C123201435 @default.
• W3100894666 hasConceptScore W3100894666C124101348 @default.
• W3100894666 hasConceptScore W3100894666C15744967 @default.
• W3100894666 hasConceptScore W3100894666C162324750 @default.
• W3100894666 hasConceptScore W3100894666C175444787 @default.
• W3100894666 hasConceptScore W3100894666C17744445 @default.
• W3100894666 hasConceptScore W3100894666C193934123 @default.
• W3100894666 hasConceptScore W3100894666C199539241 @default.
• W3100894666 hasConceptScore W3100894666C23130292 @default.
• W3100894666 hasConceptScore W3100894666C2524010 @default.
• W3100894666 hasConceptScore W3100894666C2776768071 @default.
• W3100894666 hasConceptScore W3100894666C2778496695 @default.
• W3100894666 hasConceptScore W3100894666C2781249084 @default.
• W3100894666 hasConceptScore W3100894666C2994541713 @default.
• W3100894666 hasConceptScore W3100894666C3017597292 @default.
• W3100894666 hasConceptScore W3100894666C33923547 @default.
• W3100894666 hasConceptScore W3100894666C38652104 @default.
• W3100894666 hasConceptScore W3100894666C41008148 @default.
• W3100894666 hasConceptScore W3100894666C77805123 @default.
• W3100894666 hasFunder F4320321543 @default.
• W3100894666 hasLocation W31008946661 @default.
• W3100894666 hasLocation W31008946662 @default.
• W3100894666 hasLocation W31008946663 @default.
• W3100894666 hasOpenAccess W3100894666 @default.
• W3100894666 hasPrimaryLocation W31008946661 @default.
• W3100894666 hasRelatedWork W1490610745 @default.
• W3100894666 hasRelatedWork W1591172238 @default.
• W3100894666 hasRelatedWork W1604044185 @default.
• W3100894666 hasRelatedWork W2116878667 @default.
• W3100894666 hasRelatedWork W2361239238 @default.
• W3100894666 hasRelatedWork W2626007443 @default.
• W3100894666 hasRelatedWork W2883839261 @default.
• W3100894666 hasRelatedWork W2899211198 @default.
• W3100894666 hasRelatedWork W4225340788 @default.
• W3100894666 hasRelatedWork W4318485713 @default.
• W3100894666 isParatext "false" @default.

• next