Search

Your search keyword '"Zhu, Wenbin"' showing total 1,194 results
Start Over Author "Zhu, Wenbin"
1,194 results on '"Zhu, Wenbin"'

4. COVER: A Heuristic Greedy Adversarial Attack on Prompt-based Learning in Language Models

Author

Tan, Zihao, Chen, Qingliang, Zhu, Wenbin, and Huang, Yongjian

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Prompt-based learning has been proved to be an effective way in pre-trained language models (PLMs), especially in low-resource scenarios like few-shot settings. However, the trustworthiness of PLMs is of paramount significance and potential vulnerabilities have been shown in prompt-based templates that could mislead the predictions of language models, causing serious security concerns. In this paper, we will shed light on some vulnerabilities of PLMs, by proposing a prompt-based adversarial attack on manual templates in black box scenarios. First of all, we design character-level and word-level heuristic approaches to break manual templates separately. Then we present a greedy algorithm for the attack based on the above heuristic destructive approaches. Finally, we evaluate our approach with the classification tasks on three variants of BERT series models and eight datasets. And comprehensive experimental results justify the effectiveness of our approach in terms of attack success rate and attack speed.

Published
2023

7. COVER: A Heuristic Greedy Adversarial Attack on Prompt-Based Learning in Language Models

Author

Tan, Zihao, Chen, Qingliang, Zhu, Wenbin, Huang, Yongjian, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Liu, Fenrong, editor, Sadanandan, Arun Anand, editor, Pham, Duc Nghia, editor, Mursanto, Petrus, editor, and Lukose, Dickson, editor

Published
2024
Full Text
View/download PDF

14. Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation

Author

Zhu, Wenbin, Wang, Chien-Yi, Tseng, Kuan-Lun, Lai, Shang-Hong, and Wang, Baoyuan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Due to the rising concern of data privacy, it's reasonable to assume the local client data can't be transferred to a centralized server, nor their associated identity label is provided. To support continuous learning and fill the last-mile quality gap, we introduce a new problem setup called Local-Adaptive Face Recognition (LaFR). Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model. We achieve this by a newly proposed embedding cluster model based on Graph Convolution Network (GCN), which is trained via meta-optimization procedure. Compared with previous works, our meta-clustering model can generalize well in unseen local environments. With the pseudo identity labels from the clustering results, we further introduce novel regularization techniques to improve the model adaptation performance. Extensive experiments on racial and internal sensor adaptation demonstrate that our proposed solution is more effective for adapting face recognition models in each specific environment. Meanwhile, we show that LaFR can further improve the global model by a simple federated aggregation over the updated local models., Comment: CVPR 2022

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results