Jiahui Wang

Jiahui Wang

Auto-generated profile, based on publicly available information

Jiahui Wang

State Key Laboratory of Networking and Switching Technology, National Engineering Research Center of Disaster Backup and Recovery, Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 June 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HGHaoran Gao
Haoran Gao
HZHua Zhang
Hua Zhang
JWJiahui Wang
Jiahui Wang
XZXin Zhang
Xin Zhang
HWHuawei Wang
Huawei Wang
TTTengfei Tu
Tengfei Tu
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 November 2024 in Neurocomputing
Verified
Journal Article
Closed access
HZHua Zhang
Hua Zhang
JWJiahui Wang
Jiahui Wang
HGHaoran Gao
Haoran Gao
XZXin Zhang
Xin Zhang
HWHuawei Wang
Huawei Wang
WLWenmin Li
Wenmin Li

1 January 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
JWJiahui Wang
Jiahui Wang
HZHua Zhang
Hua Zhang
YWYongji Wang
Yongji Wang
HGHaoran Gao
Haoran Gao
QLQi Li
Qi Li
HZHuiyu Zhou
Huiyu Zhou

8 June 2023 in Neural Networks
Verified
Journal Article
Closed access
HGHaoran Gao
Haoran Gao
HZHua Zhang
Hua Zhang
XZXin Zhang
Xin Zhang
WLWenmin Li
Wenmin Li
JWJiahui Wang
Jiahui Wang
FGFei Gao
Fei Gao

9 November 2026
Verified
Conference Paper
Open access
ZLZhenyan Liu
Zhenyan Liu
HZHua Zhang
Hua Zhang
HGHaoran Gao
Haoran Gao
QLQi Li
Qi Li
ZHZhu Hongliang
Zhu Hongliang
JWJiahui Wang
Jiahui Wang