Adversarial Robustness in Zero-Shot Learning: An Empirical Study on Class and Concept-Level Vulnerabilities
IEEE Transactions on Image Processing · 2026 · 35 · 8322-8337
DOI: 10.1109/tip.2026.3709493 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Zihan Ye und 5 weiteren Autor:innen. Die Arbeit nennt 84 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Ye, Z., Peng, Z., Gowda, S. N., Yan, Y., Xu, H., & Shao, L. (2026). Adversarial Robustness in Zero-Shot Learning: An Empirical Study on Class and Concept-Level Vulnerabilities. IEEE Transactions on Image Processing, 35, 8322-8337. https://doi.org/10.1109/tip.2026.3709493
Vancouver
Ye Z, Peng Z, Gowda SN, Yan Y, Xu H, Shao L. Adversarial Robustness in Zero-Shot Learning: An Empirical Study on Class and Concept-Level Vulnerabilities. IEEE Transactions on Image Processing. 2026;35:8322-8337. doi:10.1109/tip.2026.3709493
BibTeX
@article{Ye2026,
author = {Ye, Zihan and Peng, Zhiyuan and Gowda, Shreyank N and Yan, Yuping and Xu, Haotian and Shao, Ling},
title = {Adversarial Robustness in Zero-Shot Learning: An Empirical Study on Class and Concept-Level Vulnerabilities},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {8322--8337},
doi = {10.1109/tip.2026.3709493}
}
EUVIMED