Haibin Zheng

Dr. Haibin Zheng

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
30 March 2022 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
GHGuohan Huang
Guohan Huang
HZHaibin Zheng
Haibin Zheng
SYShanqing Yu
Shanqing Yu
WJWenrong Jiang
Wenrong Jiang
CCChen Cui
Chen Cui
Graph neural network (GNN) has achieved great success on graph representation learning. Challenged by large-scale private data collected from user side, GNN may not be able to reflect the excellent performance, without rich features and complete adjacent relationships. Addressing the problem, vertical federated learning (VFL) is proposed to implement local data protection through training a global model collaboratively. Consequently, for graph-structured data, it is a natural idea to construct a GNN-based VFL (GVFL) framework. However, GNN has been proven vulnerable to adversarial attacks. Whether the vulnerability will be brought into the GVFL has not been studied. This is the first study of adversarial attacks on GVFL. A novel adversarial attack method is proposed, named Graph-Fraudster. It generates adversarial perturbations based on the noise-added global node embeddings via the privacy leakage and the gradient of pairwise node. Specifically, first, Graph-Fraudster steals the global node embeddings and sets up a shadow model of the server for the attack generator. Second, noise is added into node embeddings to confuse the shadow model. Finally, the gradient of pairwise node is used to generate attacks with the guidance of noise-added node embeddings. Extensive experiments on five benchmark datasets demonstrate that Graph-Fraudster achieves the state-of-the-art attack performance compared with baselines in different GNN based GVFLs. Furthermore, Graph-Fraudster can remain a threat to GVFL even if two possible defense mechanisms are applied. In addition, some suggestions are put forward for the future work to improve the robustness of GVFL. The code and datasets can be downloaded at https://github.com/hgh0545/Graph-Fraudster.

26 April 2023 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
HZHaibin Zheng
Haibin Zheng
HXHaiyang Xiong
Haiyang Xiong
JCJinyin Chen
Jinyin Chen
HMHaonan Ma
Haonan Ma
GHGuohan Huang
Guohan Huang
Graph neural network (GNN) with a powerful representation capability has been widely applied to various areas. Recent works have exposed that GNN is vulnerable to the backdoor attack, i.e., models trained with maliciously crafted training samples are easily fooled by patched samples. Most of the proposed studies launch the backdoor attack using a trigger that is either the randomly generated subgraph e.g., erdős-rényi backdoor (ER-B) for less computational burden or the gradient-based generative subgraph e.g., graph trojaning attack (GTA) to enable a more effective attack. However, the interpretation of how is the trigger structure and the effect of the backdoor attack related has been overlooked in the current literature. Motifs, recurrent and statistically significant subgraphs in graphs, contain rich structure information. In this article, we are rethinking the trigger from the perspective of motifs and propose a motif-based backdoor attack, denoted as Motif-Backdoor . It contributes from three aspects. First, Interpretation , it provides an in-depth explanation for backdoor effectiveness by the validity of the trigger structure from motifs, leading to some novel insights, e.g., using subgraphs that appear less frequently in the graph as the trigger can achieve better attack performance. Second, Effectiveness , Motif-Backdoor reaches the state-of-the-art (SOTA) attack performance in both black-box and defensive scenarios. Third, Efficiency , based on the graph motif distribution, Motif-Backdoor can quickly obtain an effective trigger structure without target model feedback or subgraph model generation. Extensive experimental results show that Motif-Backdoor realizes the SOTA performance on three popular models and four public datasets compared with five baselines, e.g., Motif-Backdoor improves the attack success rate (ASR) by 14.73% compared with baselines on average. In addition, under a possible defense, Motif-Backdoor still implements satisfying performance, highlighting the requirement of defenses against backdoor attacks on GNNs. The datasets and code are available at https://github.com/Seaocn/Motif-Backdoor.

26 September 2023 in Computers & Security
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
MLMingjun Li
Mingjun Li
YCYao Cheng
Yao Cheng
HZHaibin Zheng
Haibin Zheng

2 November 2021 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
HZHaibin Zheng
Haibin Zheng
JCJinyin Chen
Jinyin Chen
HDHang Du
Hang Du
WZWeipeng Zhu
Weipeng Zhu
SJShouling Ji
Shouling Ji
XZXuhong Zhang
Xuhong Zhang
Despite of its tremendous popularity and success in computer vision (CV) and natural language processing, deep learning is inherently vulnerable to adversarial attacks. Many defense solutions in CV have been proposed. However, most of them, e.g., adversarial training, suffer from a low generality due to the reliance on limited adversarial examples. Moreover, some solutions even have non-negligible negative impact on the clean example classification. Last but not least, they are impotent against the unconstrained attacks. In this paper, we propose GRIP-GAN to learn a general robust inverse perturbation (GRIP), which is not only able to offset any potential adversarial perturbations but also strengthen the target class-related features, purely from the clean images via a generative adversarial network (GAN). By feeding a random noise, GRIP-GAN is able to generate a dynamic GRIP for each input image to defend against the unconstrained attacks. To further improve the defense performance, we also enable GRIP-GAN to generate a GRIP tailored to each input image. Extensive experiments are carried out on MNIST, CIFAR10, and ImageNet datasets against 17 adversarial attacks. The results show that GRIP-GAN outperforms all the baselines. We further share insights on the success of GRIP-GAN and provide visualized proofs.

19 February 2021 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
LZLongyuan Zhang
Longyuan Zhang
HZHaibin Zheng
Haibin Zheng
XWXueke Wang
Xueke Wang
ZMZhaoyan Ming
Zhaoyan Ming
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect these poisoning samples. We propose DeepPoison, a novel adversarial network of one generator and two discriminators, to address this problem. Specifically, the generator automatically extracts the target class' hidden features and embeds them into benign training samples. One discriminator controls the ratio of the poisoning perturbation. The other discriminator works as the target model to testify the poisoning effects. The novelty of DeepPoison lies in that the generated poisoned training samples are indistinguishable from the benign ones by both defensive methods and manual visual inspection, and even benign test samples can achieve the attack. Extensive experiments have shown that DeepPoison can achieve a state-of-the-art attack success rate, as high as 91.74%, with only 7% poisoned samples on publicly available datasets LFW and CASIA. Furthermore, we have experimented with high-performance defense algorithms such as autodecoder defense and DBSCAN cluster detection and showed the resilience of DeepPoison.

30 January 2023 in Information Sciences
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
HXHaiyang Xiong
Haiyang Xiong
HZHaibin Zheng
Haibin Zheng
DZDunjie Zhang
Dunjie Zhang
JZJian Zhang
Jian Zhang
YLYi Liu
Yi Liu