Picture for Cheng-Zhong Xu

Cheng-Zhong Xu

GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples

May 19, 2023
Tian Gao, Cheng-Zhong Xu, Le Zhang, Hui Kong

Access Paper or Ask Questions

Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

Mar 27, 2023
Tianrui Qin, Xitong Gao, Juanjuan Zhao, Kejiang Ye, Cheng-Zhong Xu

Figure 1 for Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

Figure 2 for Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

Figure 3 for Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

Figure 4 for Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

* UEraser introduces adversarial augmentations to suppress unlearnable example attacks and outperforms current defenses

Access Paper or Ask Questions

MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

Nov 15, 2022
Yunrui Yu, Xitong Gao, Cheng-Zhong Xu

Figure 1 for MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

Figure 2 for MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

Figure 3 for MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

Figure 4 for MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack

* To appear in NeurIPS 2022. Project repository: https://github.com/lafeat/mora

Access Paper or Ask Questions

Fine-tuning Pre-trained Language Models with Noise Stability Regularization

Jun 12, 2022
Hang Hua, Xingjian Li, Dejing Dou, Cheng-Zhong Xu, Jiebo Luo

Figure 1 for Fine-tuning Pre-trained Language Models with Noise Stability Regularization

Figure 2 for Fine-tuning Pre-trained Language Models with Noise Stability Regularization

Figure 3 for Fine-tuning Pre-trained Language Models with Noise Stability Regularization

Figure 4 for Fine-tuning Pre-trained Language Models with Noise Stability Regularization

* Preprint. Under Review

Access Paper or Ask Questions