Trustworthy Machine Learning for Web Information Systems
a special topic track of the 25
th International
Web Information Systems Engineering conference (WISE 2024)
2-5 December 2024, Qatar University, Doha, Qatar.
The special track “Trustworthy Machine Learning for Web Information Systems”
aims to address the pivotal challenges and opportunities that arise at the
intersection of trustworthy machine learning and web information systems.
As machine learning becomes increasingly integral to web technologies, ensuring these systems are
privacy-preserving, robust, secure, fair, and transparent is paramount. This track seeks to bring together a
diverse array of research contributions that explore innovative approaches to enhancing the trustworthiness
of
machine learning based web information systems. Topics of interest include, but are not limited to, privacy
enhancing technologies, robustness against adversarial attacks, fairness and bias mitigation, transparency
and
explainability in the context of web information systems. We expect to gather researchers from academia and
industry to present the latest advances and future directions in designing, deploying secure and trustworthy
machine learning algorithms, techniques, and protocols for real-world web applications, services, and
systems.
In this track, we solicit research papers and position papers to investigate best practices, new methods,
and
secure design principles. Ultimately, the goal is to advance the state of the art in creating machine
learning
based web systems that are not only technically proficient but also ethically sound, socially responsible,
and
trusted by users and stakeholders alike.
Topics of Interest
Areas of interest include (but not limited to):
- Adversarial/poisoning threats against AI/ML based web applications and systems
- Defences to improve deep learning web system robustness
- Privacy-preserving machine learning algorithms and protocols for web applications and information systems
- Privacy inference attacks against AI/ML based web systems, e.g., membership inference, model extraction,
model inversion
- Intersection among fairness, privacy, robustness, explainability, accountability, and environmental
wellbeings in AI/ML powered web systems
- Secure federated learning for decentralised and collaborative web applications and systems
- Methodologies for detecting, measuring, and mitigating bias in machine learning models, with a focus on web
applications
- Ethical implications of deploying machine learning in web systems, including considerations of user consent,
data protection, and societal impacts
- Application of machine learning to detect, prevent, and respond to cyber threats in web systems
- Studies focusing on the user perspective in ML powered web systems, including user studies, trust modeling,
and user experience design
- Development of benchmarks, datasets, and evaluation frameworks specifically designed for assessing the
trustworthiness of machine learning in web information systems.
Submission Guidelines
Papers should be submitted in PDF format. The results described must be unpublished and must not be under review
elsewhere. Submissions must conform to Springer's LNCS format format and should not exceed 15 pages, including
all
text, figures, references, and appendices. Submissions not conforming to the LNCS format, exceeding 15 pages, or
being obviously out of the scope of the conference, will be rejected without review. Information about the
Springer LNCS format can be found at
Springer.
Three to five keywords characterizing the paper should be
indicated at the end of the abstract.
All submissions must go through EasyChair system via
Easychair.
Policies
Dual Submission
It is not appropriate to submit papers that are identical (or substantially similar) to versions that have been
previously published, accepted for publication, or submitted in parallel to other conferences or journals. Such
submissions violate our dual submission policy, and the organizers have the right to reject such submissions, or
to remove them from the proceedings.
Changes of Title / Abstract / Authorship
Authors should include a full title for their paper, as well as a complete abstract by the abstract submission
deadline. Submission titles should not be modified after the abstract submission deadline, and abstracts should
not be modified by more than 50% after the abstract submission deadline. Submissions violating these rules may
be deleted after the paper submission deadline without reviewing. The author list at the submission deadline
will be considered final, and no changes in authorship will be permitted for accepted papers.
Reviewing Criteria
Accepted papers must contain significant novel results. Results can be either theoretical or empirical. Results
will be judged on the degree to which they have been objectively established and/or their potential for
scientific and technological impact. Reproducibility of results and easy availability of code will be taken into
account in the decision-making process.
Important Dates
- Submission Deadline:
30 June, 2024,
30 July, 2024 (hard deadline)
- Acceptance/Rejection Notification: 30 August, 2024
- Camera-Ready Files Submission Deadline: 07 September, 2024
Publication
Please note that for every accepted paper, it is required that at least one person registers for the conference
and presents the paper. All accepted papers will be included in the proceedings published as Springer’s LNCS
series.
Program Committee
Anjia Yang, Jinan University
Guangdong Bai, The University of Queensland
Hagen Lauer, Technische Hochschule Mittelhessen - University of Applied Sciences
He Zhang, Monash University
Jin Hong, The University of Western Australia
Leo Zhang, Griffith University
M.A.P. Chamikara, CSIRO’s Data61
Niklas Bunzel, Fraunhofer SIT / ATHENE
Shangqi Lai, CSIRO’s Data61
Sharif Abuadbba, CSIRO’s Data61
Siqi Ma, The University of New South Wales
Viet Vo, Monash University
Xiaoning Liu, RMIT University
Yaxing Chen, Northwestern Polytechnical University
Yifeng Zheng, Harbin Institute of Technology
Yu Guo, Beijing Institute of Technology
Yuan Zhang, University of Electronic Science and Technology of China
Ziyao Liu, Nanyang Technological University