Yu Zhe

According to our database, Yu Zhe authored at least 6 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy.

Junhao Wei, Yu Zhe, Jun Sakuma

CoRR, March, 2025

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors.

Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe, Yan-Lun Chen, Chih-Hsun Lin, Chia-Mu Yu, Yang Zhang, Chun-Ying Huang, Jun Sakuma

CoRR, January, 2025

2024

Parameter Matching Attack: Enhancing Practical Applicability of Availability Attacks.

Yu Zhe, Jun Sakuma

CoRR, 2024

Adversarial Attacks on Hidden Tasks in Multi-Task Learning.

Yu Zhe, Rei Nagaike, Daiki Nishiyama, Kazuto Fukuchi, Jun Sakuma

CoRR, 2024

Zero-shot domain adaptation based on dual-level mix and contrast.

Yu Zhe, Jun Sakuma

Proceedings of the IEEE Conference on Artificial Intelligence, 2024

2022

Domain Generalization Via Adversarially Learned Novel Domains.

Yu Zhe, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma

Proceedings of the IEEE International Conference on Multimedia and Expo, 2022