Zhongwang Fu
Zhongwang Fu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Xiaohui Cui
Science Center for Future Foods, Jiangnan University, Wuxi 214122, China
3 shared publications - Adnan Iftekhar
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430072, China
1 shared publication - Chengliang Zheng
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430072, China
1 shared publication - Leiyang Chen
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
1 shared publication - Liang Dong
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430072, China
1 shared publication - Yiping Yang
Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- 22 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 249
Leveraging saliency priors and explanations for enhanced consistent interpretability
- 22 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 249
Leveraging saliency priors and explanations for enhanced consistent interpretability
- Open Access
ELAA: An Ensemble-Learning-Based Adversarial Attack Targeting Image-Classification Model
The research on image-classification-adversarial attacks is crucial in the realm of artificial intelligence (AI) security. Most of the image-classification-adversarial attack methods are for white-box settings, demanding target model gradients and network architectures, which is less practical when facing real-world cases. However, black-box adversarial attacks immune to the above limitations and reinforcement learning (RL) seem to be a feasible solution to explore an optimized evasion policy. Unfortunately, existing RL-based works perform worse than expected in the attack success rate. In light of these challenges, we propose an ensemble-learning-based adversarial attack (ELAA) targeting image-classification models which aggregate and optimize multiple reinforcement learning (RL) base learners, which further reveals the vulnerabilities of learning-based image-classification models. Experimental results show that the attack success rate for the ensemble model is about 35% higher than for a single model. The attack success rate of ELAA is 15% higher than those of the baseline methods.
Open AccessELAA: An Ensemble-Learning-Based Adversarial Attack Targeting Image-Classification Model
The research on image-classification-adversarial attacks is crucial in the realm of artificial intelligence (AI) security. Most of the image-classification-adversarial attack methods are for white-box settings, demanding target model gradients and network architectures, which is less practical when facing real-world cases. However, black-box adversarial attacks immune to the above limitations and reinforcement learning (RL) seem to be a feasible solution to explore an optimized evasion policy. Unfortunately, existing RL-based works perform worse than expected in the attack success rate. In light of these challenges, we propose an ensemble-learning-based adversarial attack (ELAA) targeting image-classification models which aggregate and optimize multiple reinforcement learning (RL) base learners, which further reveals the vulnerabilities of learning-based image-classification models. Experimental results show that the attack success rate for the ensemble model is about 35% higher than for a single model. The attack success rate of ELAA is 15% higher than those of the baseline methods.
- Open Access
- 8 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 220274-220284
A Semantic Aware Meta-Path Model for Heterogeneous Network Representation Learning
Heterogeneous graph representation learning is to learn effective representations for nodes or (sub)graphs, which preserve node attributes and structural information. However, it is challenging to design a representation learning method for heterogeneous information networks (HINs) due to their diversity. Most of the existing HIN-oriented learning methods define a series of meta-paths. Then, they aggregate the representations learned from different meta-paths in the same hidden space. These methods do not consider semantic differences of different meta-paths, which leads to semantic confusion. And further affects the effectiveness of the learned representation. Given these issues, we introduce a Semantic Aware HIN Representation learning Network (SAHRN), which takes into account the semantics of different meta-paths. We mitigate the problem of semantic confusion by projecting nodes’ features into different hidden spaces separately according to different meta-paths. To further expand the scope of aggregation and enrich the aggregated information, we also design various variants of our model by adding layer aggregation. Extensive experiments on three standard HIN datasets show that SAHRN achieves consistent improvements compared to state-of-the-art graph representation learning methods. The experiments and analyses on each component of the model show the effectiveness of the proposed method. The source code is available on https://github.com/pingpingand/SAHRN.
- 8 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 220274-220284
Open AccessA Semantic Aware Meta-Path Model for Heterogeneous Network Representation Learning
Heterogeneous graph representation learning is to learn effective representations for nodes or (sub)graphs, which preserve node attributes and structural information. However, it is challenging to design a representation learning method for heterogeneous information networks (HINs) due to their diversity. Most of the existing HIN-oriented learning methods define a series of meta-paths. Then, they aggregate the representations learned from different meta-paths in the same hidden space. These methods do not consider semantic differences of different meta-paths, which leads to semantic confusion. And further affects the effectiveness of the learned representation. Given these issues, we introduce a Semantic Aware HIN Representation learning Network (SAHRN), which takes into account the semantics of different meta-paths. We mitigate the problem of semantic confusion by projecting nodes’ features into different hidden spaces separately according to different meta-paths. To further expand the scope of aggregation and enrich the aggregated information, we also design various variants of our model by adding layer aggregation. Extensive experiments on three standard HIN datasets show that SAHRN achieves consistent improvements compared to state-of-the-art graph representation learning methods. The experiments and analyses on each component of the model show the effectiveness of the proposed method. The source code is available on https://github.com/pingpingand/SAHRN.