The organizing committee of the International Workshop on Secure and Trustworthy Machine Unlearning Systems workshop invites you to submit innovative theoretical and practical research addressing the growing need for safe AI systems. Specifically, we are looking for work focused on machine unlearning as a means of ensuring compliance with privacy regulations and removing undesired knowledge from AI models. As AI technologies become more pervasive across various sectors, the ability to selectively forget or erase information from trained models—without retraining them from scratch—holds immense potential.

SCOPE

The International Workshop on Secure and Trustworthy Machine Unlearning Systems workshop will be held in Toulouse, France, in conjunction with the 30th European Symposium On Research in Computer Security (ESORICS 2025).

This workshop aims to bring together experts from academia, industry, and government to explore the challenges, strategies, and advances in machine unlearning. 

TOPICS OF INTEREST

We welcome submissions on topics related to, but not limited to, the following:

• Architectures and algorithms for efficient machine unlearning

• Security vulnerabilities and threats specific to machine unlearning

• Strategies for managing vulnerabilities in machine unlearning systems

• Machine unlearning for large-scale AI models (e.g., large language models, multi-modal models)

• Evaluation of machine unlearning effectiveness, including relevant metrics and testing methodologies

• Machine unlearning for data privacy and maintaining public trust

• Machine Unlearning as a Service (MUSaaS)

• Machine unlearning in distributed systems (e.g., federated unlearning)

• Real-world applications and case studies of machine unlearning in AI systems

We are also open to submissions exploring additional aspects of Secure and Trustworthy Machine Unlearning Systems.

IMPORTANT DATES

All deadlines are at 23:59 AoE (Anywhere on Earth)

• Submission Deadline: June 22, 2025

• Notification to Authors: July 19, 2025

• Camera-ready Versions Due: August 1, 2025

INSTRUCTIONS FOR PAPER SUBMISSION

• All submissions should be appropriately anonymized (i.e., papers should not contain author names, affiliations, or obvious citations).

• Submissions should be at most 16 pages in the LNCS format, including the bibliography and well-marked appendices.

• All submissions must be written in English, and only PDF files will be accepted. A LaTeX source file will be required for the final version of accepted papers.

• The final version of an accepted paper must follow the format required for publication in the LNCS series.

• Authors should consult Springer’s authors’ guidelines and use their proceedings templates.

• ORCID: Authors are encouraged to include their ORCID IDs in their papers.

• Submissions not meeting these guidelines risk rejection without consideration of their merits.

Important Notes:

• A paper submitted cannot be under review for any other conference or journal during the time it is being considered for review. After submission, you must await our response before submitting elsewhere.

• If a paper is submitted to another conference or journal either before or after submission, it will be rejected without review, and we will also notify the other conference/journal.

• This restriction applies to identical as well as substantially similar papers.

• The corresponding author of each accepted paper, acting on behalf of all of the authors, must complete and sign a Consent-to-Publish form. The corresponding author signing the copyright form should match the corresponding author marked on the paper. Once the files have been sent to Springer, changes relating to authorship cannot be made.

PROCEEDINGS The proceedings are planned to be published by Springer in the Lecture Notes in Computer Science (LNCS) series.

ATTENDANCE The workshop will be held in person, and at least one author of each accepted paper must guarantee their presence to present their paper at the workshop.

PROGRAM CHAIR

• Prof. Joachim Posegga, University of Passau, Germany

PC Co-Chairs:

• Prof. Dieter Gollmann, Hamburg University of Technology

• Prof. Kwok-Yan Lam, Nanyang Technological University

PROGRAM COMMITTEE 

See  https://www.ntu.edu.sg/dtc/esorics-workshop 

Contact

All questions about submissions should be emailed to 

jp@sec.uni-passau.de

kwokyan.lam@ntu.edu.sg