Research on the robustness of the open-world test-time training model
Our findings reveal that OWTTT algorithms lacking rigorous security assessment against such attacks are unsuitable for real-world deployment. Consequently, we strongly advocate for the integration of defenses against test-time poisoning attacks into the fundamental design of future open-world test-time training methodologies.
Authors
- Shu Pi
- Jiatian Pi (ORCID: https://orcid.org/0000-0001-8261-3609)
- Xin Wang (ORCID: https://orcid.org/0000-0002-0641-3186)
Institutions
- Chongqing Normal University (CN)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-08-04
- DOI
- https://doi.org/10.3389/frai.2025.1621025
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Chongqing
- Centre Scientifique et Technique du Bâtiment