Jiahui Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiahui Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Haoran Gao
JIUTIAN Research, China Mobile, Beijing, China
5 shared publications - Hua Zhang
Beijing University of Posts and Telecommunications
5 shared publications - Huawei Wang
Beijing Institute of Control Engineering, Beijing, China
2 shared publications - Huiyu Zhou
University of Leicester, Leicester, United Kingdom
2 shared publications - Qi Li
School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications Wenmin Li
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6962-6971
FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6962-6971
Open AccessFedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
- 19 November 2024
- Published by Elsevier in Neurocomputing
- Vol. 616
VIWHard: Text adversarial attacks based on important-word discriminator in the hard-label black-box setting
- 19 November 2024
- Published by Elsevier in Neurocomputing
- Vol. 616
VIWHard: Text adversarial attacks based on important-word discriminator in the hard-label black-box setting
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 6484-6498
NUAT-GAN: Generating Black-Box Natural Universal Adversarial Triggers for Text Classifiers Using Generative Adversarial Networks
Recent works have demonstrated that text classifiers are vulnerable to universal adversarial triggers (UATs), which are concatenated to any original text from the dataset to mislead text classifiers. Existing methods for generating UATs are limited to a white-box setting, where the adversary needs access to the gradient information about the target model. In the more practical black-box setting, the adversary can only access the logit output of the target model, which increases the difficulty of crafting UATs. In this paper, we propose a framework for generating natural UATs using generative adversarial networks (NUAT-GAN) in the black-box setting. To update parameters of the generator in the black-box setting, we design a training generator algorithm with policy gradient (TGPG), in which the gradient of the target model is replaced with the policy gradient of reinforcement learning. On three text classification datasets, we evaluate the attack and the natural performance of UATs generated on LSTM, CNN and BERT models. Results show that UATs generated by NUAT-GAN can mislead the above models. The average values of the Attack Success Rate (ASR) and GPT-2 Loss of UATs are 0.81 and 9.10, respectively. The UATs can effectively attack online models, such as AllenNLP and ChatGPT. Moreover, we replace the reward given by the discriminator with GPT-2 Loss , the attack and the natural performance of UATs are close to those of NUAT-GAN. This shows that NUAT-GAN is extensible and can combined with the language model.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 6484-6498
NUAT-GAN: Generating Black-Box Natural Universal Adversarial Triggers for Text Classifiers Using Generative Adversarial Networks
Recent works have demonstrated that text classifiers are vulnerable to universal adversarial triggers (UATs), which are concatenated to any original text from the dataset to mislead text classifiers. Existing methods for generating UATs are limited to a white-box setting, where the adversary needs access to the gradient information about the target model. In the more practical black-box setting, the adversary can only access the logit output of the target model, which increases the difficulty of crafting UATs. In this paper, we propose a framework for generating natural UATs using generative adversarial networks (NUAT-GAN) in the black-box setting. To update parameters of the generator in the black-box setting, we design a training generator algorithm with policy gradient (TGPG), in which the gradient of the target model is replaced with the policy gradient of reinforcement learning. On three text classification datasets, we evaluate the attack and the natural performance of UATs generated on LSTM, CNN and BERT models. Results show that UATs generated by NUAT-GAN can mislead the above models. The average values of the Attack Success Rate (ASR) and GPT-2 Loss of UATs are 0.81 and 9.10, respectively. The UATs can effectively attack online models, such as AllenNLP and ChatGPT. Moreover, we replace the reward given by the discriminator with GPT-2 Loss , the attack and the natural performance of UATs are close to those of NUAT-GAN. This shows that NUAT-GAN is extensible and can combined with the language model.
- 8 June 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 516-526
Enhanced covertness class discriminative universal adversarial perturbations
- 8 June 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 516-526
Enhanced covertness class discriminative universal adversarial perturbations