Home

New: Workshop  Registration

News: We are organizing a theme section of ACM TOIT (Transactions on Internet Technology) on Trust and AI. The CFP for the theme is online at https://toit.acm.org/pdf/ACM-ToIT-CfP-Trust.pdf 


The 20th edition of this international workshop will be co-located with AAMAS/IJCAI/ECAI/ICML 2018 and held in Stockholm, Sweden on July 14 2018.

Submissions should be made through easychair:  https://easychair.org/conferences/?conf=trust2018

Trust is important in many kinds of interactions, including direct or computer-mediated human interaction, human-computer interaction and among social agents; it characterizes those elements that are essential in social reliability. It also informs the selection of partners for successful multiagent coordination (for example, in robotics applications). Trust is more than communication that is robust against repudiation or interference. The reliability of information about the status of a trade partner, for example, is only partly dependent on secure communication.

With the growing prevalence of social interaction through electronic means, trust, reputation, privacy and identity become more and more important. Trust is not just a simple, monolithic concept; it is multi-faceted, operating at many levels of interaction, and playing many roles. Another growing trend is the use of reputation mechanisms, and in particular the interesting link between trust and reputation. Many computational and theoretical models and approaches to reputation have been developed in recent years (for ecommerce, social networks, blogs, etc.). Further, identity and associated trustworthiness must be ascertained for reliable interactions and transactions. Trust is foundational for the notion of agency and for its defining relation of acting "on behalf of". It is also critical for modeling and supporting groups and teams, for both organization and coordination, with the related trade-off between individual utility and collective interest. The electronic medium seems to weaken the usual bonds of social control and the disposition to cheat grows stronger: this is yet another context where trust modeling is critical.

The aim of the workshop is to bring together researchers (ideally from different disciplines) who can contribute to a better understanding of trust and reputation in agent societies. We welcome submissions of high-quality research addressing issues that are clearly relevant to trust, deception, privacy, reputation, security and control in agent-based systems, from theoretical, applied and interdisciplinary perspectives. Submitted contributions should be original and not submitted elsewhere. Papers accepted for presentation must be relevant to the workshop, and to demonstrate clear exposition, offering new ideas in suitable depth and detail. 

The scope of the workshop includes (but is not limited to):

  • Trust modeling in multiagent systems
  • Addressing misinformation in online systems
  • Engendering trust in AI systems from human users
     With more specific subtopics including (but not limited to):
    • Trust and risk-aware decision making
    • Game-theoretic models of trust
    • Trust in the context of adversarial environments
    • Deception and fraud, and its detection and prevention
    • Intrusion resilience in trusted computing
    • Reputation mechanisms
    • Trust within socio-technical systems and organizations
    • Socio-cognitive models of trust
    • Trust within service-oriented architectures
    • Human or agent trust in agent partners
    • Trust within social networks
    • AI solutions to improve online fact checking and critical thinking
    • Detecting and preventing collusion
    • Improving transparency in AI systems
    • Addressing bias in AI systems
    • Detecting and addressing mistrust of AI systems from human users
    • Realworld applications of multiagent trust modeling


    Comments