Minhao Cheng

Minhao Cheng

Auto-generated profile, based on publicly available information

Minhao Cheng

Pennsylvania State University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
7 December 2024
Verified
Book Chapter
Closed access
PDF file
RMRui Min
Rui Min
SLSen Li
Sen Li
HCHongyang Chen
Hongyang Chen
MCMinhao Cheng
Minhao Cheng

4 August 2023
Verified
Conference Paper
Open access
ZQZeyu Qin
Zeyu Qin
LYLiuyi Yao
Liuyi Yao
DCDaoyuan Chen
Daoyuan Chen
YLYaliang Li
Yaliang Li
BDBolin Ding
Bolin Ding
MCMinhao Cheng
Minhao Cheng
In this work, besides improving prediction accuracy, we study whether personalization could bring robustness benefits to backdoor attacks. We conduct the first study of backdoor attacks in the pFL framework, testing 4 widely used backdoor attacks against 6 pFL methods on benchmark datasets FEMNIST and CIFAR-10, a total of 600 experiments. The study shows that pFL methods with partial model-sharing can significantly boost robustness against backdoor attacks. In contrast, pFL methods with full model-sharing do not show robustness. To analyze the reasons for varying robustness performances, we provide comprehensive ablation studies on different pFL methods. Based on our findings, we further propose a lightweight defense method, Simple-Tuning, which empirically improves defense performance against backdoor attacks. We believe that our work could provide both guidance for pFL application in terms of its robustness and offer valuable insights to design more robust FL methods in the future. We open-source our code to establish the first benchmark for black-box backdoor attacks in pFL: https://github.com/alibaba/FederatedScope/tree/backdoor-bench.

24 November 2024
Verified
Book Chapter
Closed access
PDF file
YBYuanhao Ban
Yuanhao Ban
RWRuochen Wang
Ruochen Wang
TZTianyi Zhou
Tianyi Zhou
MCMinhao Cheng
Minhao Cheng
BGBoqing Gong
Boqing Gong
CHCho-Jui Hsieh
Cho-Jui Hsieh

1 January 2024
Verified
Conference Paper
Open access
PDF file
LLLiying Li
Liying Li
YBYihan Bai
Yihan Bai
MCMinhao Cheng
Minhao Cheng
Liying Li, Yihan Bai, Minhao Cheng. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.


24 August 2024
Verified
Conference Paper
Open access
HWHaosen Wang
Haosen Wang
CXCan Xu
Can Xu
CSChenglong Shi
Chenglong Shi
PZPengfei Zheng
Pengfei Zheng
SZShiming Zhang
Shiming Zhang
HCHongyang Chen
Hongyang Chen
Self-supervised learning (SSL) has become one of the most popular learning paradigms and has achieved remarkable success in the graph field. Recently, a series of pre-training studies on heterogeneous graphs (HGs) using SSL have been proposed considering the heterogeneity of real-world graph data. However, verification of the robustness of heterogeneous graph pre-training is still a research gap. Most existing researches focus on supervised attacks on graphs, which are limited to a specific scenario and will not work when labels are not available. In this paper, we propose a novel unsupervised heterogeneous graph rewriting attack via node clustering (HGAC) that can effectively attack HG pre-training models without using labels. Specifically, a heterogeneous edge rewriting strategy is designed to ensure the rationality and concealment of the attacks. Then, a tailored heterogeneous graph contrastive learning (HGCL) is used as a surrogate model. Moreover, we leverage node clustering results of the clean HGs as the pseudo-labels to guide the optimization of structural attacks. Extensive experiments exhibit powerful attack performances of our HGAC on various downstream tasks (i.e., node classification, node clustering, metapath prediction, and visualization) under poisoning attack and evasion attack.