The Security in Machine Learning and its Applications (SiMLA) workshop provides a dedicated forum to address the critical challenges of securing modern machine learning (ML) systems. With ML technologies increasingly deployed in domains such as autonomous driving, biometric authentication, and intelligent surveillance, their vulnerabilities to adversarial attacks, data poisoning, and privacy breaches raise significant concerns. SiMLA 2026 aims to bring together researchers and practitioners to exchange ideas, present novel techniques, and discuss emerging threats in trustworthy ML. Topics of interest include adversarial learning, privacy-preserving ML, secure deployment, robustness certification, model provenance, and the security of large language models. This year, SiMLA also highlights the growing importance of safeguarding Artificial General Intelligence (AGI) and AI agents, with emphasis on content provenance, mis/disinformation detection, and safe agent deployment. Building on the success of previous editions, the workshop will foster interactive discussions and advance the state of the art in secure and resilient machine learning.

Submission Guidelines

Submissions must not substantially duplicate work that any of the authors has published elsewhere or has submitted in parallel to any other venue with formally published proceedings. Information about submissions may be shared with program chairs of other conferences for that purpose. Submissions must be anonymous, with no author names, affiliations, acknowledgement or obvious references. Each submission must begin with a title, short abstract, and a list of keywords. The introduction should summarize the contributions of the paper at a level appropriate for a non-specialist reader. All submissions must follow the original LNCS format with a page limit of 20 pages (incl. references). Authors of accepted papers must guarantee that their paper will be presented at the conference and must make a full version of their paper available online. Submissions not meeting the submission guidelines risk rejection without consideration of their merits. It is strongly encouraged that submissions be processed in LaTeX.

Work-in-progress papers are welcome, and such submissions can expectedly be less than the maximum page limit of 20 pages. Submissions less than 10 pages, however, are discouraged as there is not enough space for appropriate technical content presentation. Authors are required to include "WiP:" in the title of a work-in-progress paper submission.

Committees

Program Committee

• Yanjun Zhang, University of Technology Sydney, Australia
• Zirui Gong, Griffith University, Australia
• Dayong Ye, City University of Macau, Macau
• Yufei Chen, City University of Hong Kong, Hong Kong
• Shuren Qi, The Chinese University of Hong Kong, Hong Kong
• Maggie Liu, RMIT University, Australia
• Daniël Reijsbergen, Singapore University of Technology and Design, Singapore
• Yuantian Miao, The University of Newcastle, Australia
• Zhongyun Hua, Harbin Institute of Technology, China
• Yushu Zhang, Jiangxi University of Finance and Economics, China
• Chuan Qin, University of Shanghai for Science and Technology, China
• Jiaojiao Jiang, University of New South Wales, Australia
• Nan Wang, CSIRO, Australia
• Shangqi Lai, University of Melbourne, Australia
• Naipeng Dong, The University of Queensland, Australia
• Viet Vo, Swinburne University of Technology, Australia
• Yang Cao, Tokyo Institute of Technology, Japan
• Yu Li, Zhejiang University, China
• Yansong Gao, University of Western Australia, Australia
• Xiaoyong Yuan, Clemson University, USA
• Junxu Liu, The Hong Kong Polytechnic University, Hong Kong
• Chenxi Qiu, University of North Texas, USA

Organizing committee

• Leo Zhang, leo.zhang@griffith.edu.au, Griffith University, Australia
• Yifeng Zheng, yifeng.zheng@polyu.edu.hk, The Hong Kong Polytechnic University, Hong Kong
• Fuyi Wang, fuyi.wang@rmit.edu.au, RMIT University, Australia

Contact

All questions about submissions should be emailed to Leo Zhang, leo.zhang@griffith.edu.au, Griffith University, Australia