Please login to be able to save your searches and receive alerts for new content matching your search criteria.
A user's review of an app often describes the user's interactions with the app. These interactions, which we interpret as mini stories, are prominent in reviews with negative ratings. In general, a story in an app review would contain at least two types ...
Ethics is inherently a multiagent concern. However, research on AI ethics today is dominated by work on individual agents: (1) how an autonomous robot or car may harm or (differentially) benefit people in hypothetical situations (the so-called trolley ...
An interaction protocol specifies a decentralized multiagent system operationally by specifying constraints on messages exchanged by its member agents. Engineering with protocols requires support for a notion of refinement, whereby a protocol may be ...
We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through ...
We address the problem of engineering a sociotechnical system (STS) with respect to its stakeholders’ requirements. We motivate a two-tier STS conception composed of a technical tier that provides control mechanisms and describes what actions are ...
Commitments capture how an agent relates to another agent, whereas goals describe states of the world that an agent is motivated to bring about. Commitments are elements of the social state of a set of agents whereas goals are elements of the private ...
Advances in AI techniques and computing platforms have triggered a lively and expanding discourse on ethical decision making by autonomous agents. Much recent work in AI concentrates on the challenges of moral decision making from a decision-theoretic ...
An interaction protocol specifies the constraints on communication between agents in a multiagent system. Ideally, we would like to be able to treat protocols as modules and compose them in a declarative manner to systematically build more complex ...
We propose and evaluate an information extraction and analysis framework that combines human intelligent (crowdsourcing) with automated methods to produce improved security and privacy requirements incorporating knowledge from post-deployment artifacts ...
We address the problem of designing privacy-preserving ethical personal agents that understand and act according to their users' preferred values and ethical principles, and provide a satisfying social experience to all their stakeholders.
Unsolicited patient complaints expressed in patients' own words provide an evidential basis for identifying and mitigating patient safety and financial risks associated with physicians and other practitioners. Classifying patient complaints is ...
The Blindingly Simple Protocol Language (BSPL) is a novel information-based approach for specifying interaction protocols that can be enacted by agents in a fully decentralized manner via asynchronous messaging. We introduce Splee, an extension of BSPL. ...
We seek to address the challenge of engineering socially intelligent personal agents that are privacy-aware. We propose Arnor, a method, including a metamodel based on social constructs. Arnor incorporates social norms and goes beyond existing agent-...
Norms provide a way to model the social architecture of a sociotechnical system (STS) and are thus crucial for understanding how such a system supports secure collaboration between principals, that is, autonomous parties such as humans and ...
Secure collaboration requires the collaborating parties to apply the right policies for their interaction. We adopt a notion of conditional, directed norms as a way to capture the standards of correctness for a collaboration. How can we handle ...
The overarching vision of social machines is to facilitate social processes by having computers provide administrative support. We conceive of a social machine as a sociotechnical system (STS): a software-supported system in which autonomous principals ...
The social state of a system of interacting principals is given by the set of social relationships among them. These relationships not only arise due to social interactions but also influence those interactions. For specificity, we restrict ourselves to ...
The science of cybersecurity has recently been garnering much attention among researchers and practitioners dissatisfied with the ad hoc nature of much of the existing work on cybersecurity. Cybersecurity offers a great opportunity for multiagent ...
Norms are a promising basis for governance in secure, collaborative environments---systems in which multiple principals interact. Yet, many aspects of norm-governance remain poorly understood, inhibiting adoption in real-life collaborative systems. This ...
We understand a sociotechnical system as a multistakeholder cyber-physical system. We introduce governance as the administration of such a system by the stakeholders themselves. In this regard, governance is a peer-to-peer notion and contrasts with ...