Liz Sonenberg

Directive Explanations for Actionable Explainability in Machine Learning Applications

Ronal Singh, Tim Miller, Henrietta Lyons, Liz Sonenberg, Eduardo Velloso, Frank Vetere, Piers Howe, Paul Dourish

Journal article  |  2023  |  ACM Transactions on Interactive Intelligent Systems

In this paper, we show that explanations of decisions made by machine learning systems can be improved by not only explaining ..

Efficient multi-agent epistemic planning: Teaching planners about nested belief

Christian Muise, Vaishak Belle, Paolo Felli, Sheila McIlraith, Tim Miller, Adrian R Pearce, Liz Sonenberg

Journal article  |  2021  |  ARTIFICIAL INTELLIGENCE

Many AI applications involve the interaction of multiple autonomous agents, requiring those agents to reason about their own belie..

Modeling communication of collaborative multiagent system under epistemic planning

Abeer Alshehri, Tim Miller, Liz Sonenberg

Journal article  |  2021  |  INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS

In most multiagent applications, communication is essential among agents to coordinate their actions and achieve their goals. Howe..

The Role of Environments in Affording Deceptive Behaviour: Some Preliminary Insights from Stage Magic

W Smith, M Kirley, L Sonenberg, F Dignum

Book Chapter  |  2021  |  Communications in Computer and Information Science

Drawing on an ecological perspective, we contend that research into deception in AI needs to consider not only the cognitive struc..

Strengthening Australia’s cybersecurity regulations and incentives: Response to the Department of Home Affairs Discussion Paper

Amit Achrekar, Atif Ahmad, Shanton Chang, Shaanan Cohney, Suelette Dreyfus, Chris Leckie, Toby Murray, Jeannie Paterson, Van Thuan Pham, Elizabeth Sonenberg

Report  |  2021

The development of the regulatory and incentives framework is a key opportunity to align Australian enterprises’ cybersecurity pra..

Characterising Deception in AI: A Survey

P Masters, W Smith, L Sonenberg, M Kirley

Book Chapter  |  2021  |  Communications in Computer and Information Science

In 2000, it was predicted that artificially intelligent agents would inevitably become deceptive. Today, in a world seemingly awas..

Designing Multi-Agent System Organisations for Flexible Runtime Behaviour

Kathleen Keogh, Liz Sonenberg

Journal article  |  2020  |  APPLIED SCIENCES-BASEL

We address the challenge of multi-agent system (MAS) design for organisations of agents acting in dynamic and uncertain environmen..

Combining gaze and AI planning for online human intention recognition

R Singh, T Miller, J Newn, E Velloso, F Vetere, L Sonenberg

Journal article  |  2020  |  Artificial Intelligence

Intention recognition is the process of using behavioural cues, such as deliberative actions, eye gaze, and gestures, to infer an ..

Demand-Driven Transparency for Monitoring Intelligent Agents

Mor Vered, Piers Howe, Tim Miller, Liz Sonenberg, Eduardo Velloso

Journal article  |  2020  |  IEEE Transactions on Human-Machine Systems

In autonomous multiagent or multirobotic systems, the ability to quickly and accurately respond to threats and uncertainties is im..

Explainable Reinforcement Learning through a Causal Lens

Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere

Journal article  |  2020  |  THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

Prominent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal rel..