Securing foundation models: Failure cases, challenges, and the future

Author

Mengjia NIU
Jiawen ZHU
Hezhe QIAO
Hamed HADDADI
Guansong PANG, Singapore Management UniversityFollow

Publication Type

Journal Article

Publication Date

9-2025

Abstract

Foundation models (FMs), trained on diverse web-scale datasets, have demonstrated remarkable performance on a broad range of tasks. Despite their strong capabilities, the rapid expansion in scale and complexity of FMs introduces significant challenges that could compromise their reliability upon deployment. Key concerns can include the potential leakage of private data, exacerbation of existing bias, generation of incorrect or even harmful responses, and the risk of malicious use, among other emerging issues. This article discusses the public perception of critical ethical issues surrounding the privacy, safety, and security of FMs and their major challenges and opportunities.

Discipline

Artificial Intelligence and Robotics | Information Security

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE Intelligent Systems

Volume

40

Issue

5

First Page

52

Last Page

56

ISSN

1541-1672

Identifier

10.1109/MIS.2025.3597124

Publisher

Institute of Electrical and Electronics Engineers

Citation

NIU, Mengjia; ZHU, Jiawen; QIAO, Hezhe; HADDADI, Hamed; and PANG, Guansong. Securing foundation models: Failure cases, challenges, and the future. (2025). IEEE Intelligent Systems. 40, (5), 52-56.
Available at: https://ink.library.smu.edu.sg/sis_research/10981

Additional URL

https://doi.org/10.1109/MIS.2025.3597124