CHAI: Cyber Hygiene in AI enabled domestic life
Lead Research Organisation:
University of Bristol
Department Name: Engineering Mathematics and Technology
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
People |
ORCID iD |
| Weiru Liu (Principal Investigator) |
Publications
McAreavey K
(2022)
A Smart Home Testbed for Evaluating XAI with Non-experts
Vasalou A
(2024)
In pursuit of thermal comfort: An exploration of smart heating in everyday life
in International Journal of Human-Computer Studies
Vasalou A
(2025)
Doing cybersecurity at home: A human-centred approach for mitigating attacks in AI-enabled home devices
in Computers & Security
| Description | Explainable AI is very much user-facing research and development, especially for non-expert users. Through our theoretical research, user-interface design and implementation, and extensive user evaluations with over 300 randomly selected users via the Prolific platform for two studies, we discovered that integrating some principles from psychology, cognitive science,, social science, HCI into XAI design is very important for users' satisfaction and understanding. |
| Exploitation Route | Through workshops and events that include AI practitioners, policy makers, AI technology developers and researchers from psychology, cognitive science,, social science, HCI to understand how explanations shall be presented to users. |
| Sectors | Digital/Communication/Information Technologies (including Software) |
| Description | EPSRC IAA fund: Enhancing transparency and trust in AI systems through explanations for non-expert users: with domestic energy management as a use case |
| Amount | £14,938 (GBP) |
| Organisation | University of Bristol |
| Sector | Academic/University |
| Country | United Kingdom |
| Start | 03/2023 |
| End | 05/2024 |
| Description | Learn to explain: explaining robots behaviour through contrastive explanations |
| Organisation | Sun Yat-Sen University |
| Country | China |
| Sector | Academic/University |
| PI Contribution | Based on our research outcomes in the CHAI project and on related research activities, we have successfully obtained funding from Royal Society International Exchange Scheme to further explore research in explaining surgical robots' behaviour. This is a collaborative project with Sun Yet-sen University in China. My team will develop explanation strategies for patients and clinicians about robot's actions. |
| Collaborator Contribution | The partner team will develop surgical robot scenarios, setup virtual environment for training robots and integrate our explanation strategy into the operations of such robots in simulated environment. |
| Impact | The project only started in December 2024, not outputs are published yet. |
| Start Year | 2024 |
| Title | SQUID: a platform supporting the XAI and cyber attack identification interface for energy management at homes |
| Description | This platform hosts a collection of packages and functions in the cloud that support the remote access of home energy management system and its associated XAI interfaces. It is a part of the CHAI field trial enabling end-users to interact with the underlying AI-based IoT system for smart homes with functions of XAI and cyber attach identification. A comprehensive interactive interfaces and notification pages have been developed, allowing end-users to (i) enter their own schedules for their home energy devices, (ii) to see the actual cost/savings of such changes at real-time, and (iii) to be able to identify any potential cyber attacks to the IoT system or to the devices. |
| Type Of Technology | Software |
| Year Produced | 2023 |
| Open Source License? | Yes |
| Impact | The impact is being assessed through a field trial at homes. A series of interviews have been carried out and qualitative analysis will be done soon. |
| URL | https://github.com/chai-project |
| Description | Committee member of International conference and presenting a paper at the conference: First World Conference on Explainable Artificial Intelligence |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | An international conference dedicated to presenting the latest advances and challenges in making the AI and machine learning systems understandable and transparent. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://easychair.org/cfp/XAI-2023 |
| Description | Invited talk at LV-Gi and University of Bristol workshop on Human-Machine Teaming |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Professional Practitioners |
| Results and Impact | A workshop dedicated to the discussion of how human-in-the-loop can improve AI decision making. |
| Year(s) Of Engagement Activity | 2023 |
| Description | Keynote talk at an UK National Conference: AI and Cyber Security Track |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | This was an annual conference organized by the Association of British Chinese Professors. The purpose of the conference series is to exchange advanced research results in all domains (science, engineering, social sciences, law, art and humanities). The conference also included the discussion on UK-China education collaborations and on University-Industry collaborations respectively. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://abcp.org.uk/abcp2023-ai-cybersecurity/#day1 |
| Description | Member of a Panel Discussion on Trustworthy and Responsible AI |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | This panel discussed the implications of EU AI Act and some of the UK Government documents about AI and its future development and deployment. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://abcp.org.uk/abcp2023-ai-cybersecurity/#day1 |