Ming Hu

Dr. Ming Hu

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
22 December 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
XZXinqian Zhang
Xinqian Zhang
MHMing Hu
Ming Hu
JXJun Xia
Jun Xia
TWTongquan Wei
Tongquan Wei
MCMingsong Chen
Mingsong Chen
SHShiyan Hu
Shiyan Hu
As a promising method for central model training on decentralized device data without compromising user privacy, federated learning (FL) is becoming more and more popular in Internet-of-Things (IoT) design. However, due to limited computing and memory resources of devices that restrict the capabilities of hosted deep learning models, existing FL approaches for artificial intelligence IoT (AIoT) applications suffer from inaccurate prediction results. To address this problem, this article presents a collaborative Big.Little branch architecture to enable efficient FL for AIoT applications. Inspired by the architecture of BranchyNet which has multiple prediction branches, our approach deploys deep neural network (DNN) models across both cloud and AIoT devices. Our Big.Little branch model has two branches, where the big branch is deployed on cloud for strengthened prediction accuracy, and the little branches are used to fit for AIoT devices. When AIoT devices cannot make the prediction with high confidence using local little branches, they will resort to the big branch for further inference. To increase both prediction accuracy and early exit rate of Big.Little branch model, we propose a two-stage training and coinference scheme, which considers the local characteristics of AIoT scenarios. Comprehensive experiment results obtained from a real AIoT environment demonstrate the efficiency and effectiveness of our approach in terms of prediction accuracy and average inference time.

24 July 2019 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
HGHaifeng Gu
Haifeng Gu
JZJianning Zhang
Jianning Zhang
TLTian Liu
Tian Liu
MHMing Hu
Ming Hu
JZJunlong Zhou
Junlong Zhou
MCMingsong Chen
Mingsong Chen

12 July 2024 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
KLKaixuan Li
Kaixuan Li
YXYue Xue
Yue Xue
SCSen Chen
Sen Chen
HLHan Liu
Han Liu
KSKairan Sun
Kairan Sun
YCYixiang Chen
Yixiang Chen
In recent years, the importance of smart contract security has been heightened by the increasing number of attacks against them. To address this issue, a multitude of static application security testing (SAST) tools have been proposed for detecting vulnerabilities in smart contracts. However, objectively comparing these tools to determine their effectiveness remains challenging. Existing studies often fall short due to the taxonomies and benchmarks only covering a coarse and potentially outdated set of vulnerability types, which leads to evaluations that are not entirely comprehensive and may display bias. In this paper, we fill this gap by proposing an up-to-date and fine-grained taxonomy that includes 45 unique vulnerability types for smart contracts. Taking it as a baseline, we develop an extensive benchmark that covers 40 distinct types and includes a diverse range of code characteristics, vulnerability patterns, and application scenarios. Based on them, we evaluated 8 SAST tools using this benchmark, which comprises 788 smart contract files and 10,394 vulnerabilities. Our results reveal that the existing SAST tools fail to detect around 50% of vulnerabilities in our benchmark and suffer from high false positives, with precision not surpassing 10%. We also discover that by combining the results of multiple tools, the false negative rate can be reduced effectively, at the expense of flagging 36.77 percentage points more functions. Nevertheless, many vulnerabilities, especially those beyond Access Control and Reentrancy vulnerabilities, remain undetected. We finally highlight the valuable insights from our study, hoping to provide guidance on tool development, enhancement, evaluation, and selection for developers, researchers, and practitioners.

11 December 2025 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
XZXiaoyu Zhang
Xiaoyu Zhang
CZCen Zhang
Cen Zhang
TLTianlin Li
Tianlin Li
YHYihao Huang
Yihao Huang
XJXiaojun Jia
Xiaojun Jia
SCShen Chao
Shen Chao
The systems and software powered by Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks enabling the LLM system to generate harmful content, while hijacking attacks manipulate the LLM system to perform attacker-desired tasks, underscoring the necessity for detection tools. Unfortunately, existing detecting approaches are usually tailored to specific attacks, resulting in poor generalization in detecting various attacks across different modalities. To address it, we propose JailGuard , a universal detection framework deployed on top of LLM systems for prompt-based attacks across text and image modalities. JailGuard operates on the principle that attacks are inherently less robust than benign ones. Specifically, JailGuard mutates untrusted inputs to generate variants and leverages the discrepancy of the variants’ responses on the target model to distinguish attack samples from benign samples. We implement 18 mutators for text and image inputs and design a mutator combination policy to further improve detection generalization. The evaluation on the dataset containing 15 known attack types suggests that JailGuard achieves the best detection accuracy of 86.14%/82.90% on text and image inputs, outperforming state-of-the-art methods by 11.81–25.73% and 12.20–21.40%.

13 May 2024
Verified
Conference Paper
Closed access
MHMing Hu
Ming Hu
PZPeiheng Zhou
Peiheng Zhou
ZYZhihao Yue
Zhihao Yue
ZLZhiwei Ling
Zhiwei Ling
YHYihao Huang
Yihao Huang
MCMingsong Chen
Mingsong Chen
As a promising distributed machine learning paradigm, Federated Learning (FL) has attracted increasing attention to deal with data silo problems without compromising user privacy. By adopting the classic one-to-multi training scheme (i.e., FedAvg), where the cloud server dispatches one single global model to multiple involved clients, conventional FL methods can achieve collaborative model training without data sharing. However, since only one global model cannot always accommodate all the incompatible convergence directions of local models, existing FL approaches greatly suffer from inferior classification accuracy. To address this issue, we present an efficient FL framework named FedCross, which uses a novel multi-to-multi FL training scheme based on our proposed multi-model cross-aggregation approach. Unlike traditional FL methods, in each round of FL training, FedCross uses multiple middleware models to conduct weighted fusion individually. Since the middleware models used by FedCross can quickly converge into the same flat valley in terms of loss landscapes, the generated global model can achieve a well-generalization. Experimental results on various well-known datasets show that, compared with state-of-the-art FL methods, Fed Cross can significantly improve FL accuracy within both IID and non-IID scenarios without causing additional communication overhead.

10 April 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
MHMing Hu
Ming Hu
ECE. Cao
E. Cao
HHHongbing Huang
Hongbing Huang
MZMin Zhang
Min Zhang
XCXiaohong Chen
Xiaohong Chen
MCMingsong Chen
Mingsong Chen
Due to deeply intertwined physical and hardware/software components together with increasing number of interconnected heterogeneous devices powered by Artificial Intelligence (AI) techniques, the design complexity of Cyber-Physical Systems (CPSs) becomes skyrocketing. Model-Driven Engineering (MDE) methods have been proven to be effective in increasing the productivity of CPS design. However, there is still a lack of MDE approaches that enable design space exploration as well as the code generation for the design of AI IoT (AIoT)-based CPSs. To mitigate the situation, this paper presents a unified modeling language named AIoTML for AIoT-based CPSs, which enables the construction of AI-based components across different modeling levels for the purposes of intelligent sensing and control. By extending the constructs of state-of-the-art Domain-Specific Language (DSL) ThingML, AIoTML can seamlessly unify the modeling of both autonomous executions of AIoT devices and their surrounding physical environment, which facilitates both platform-independent simulation and control optimization for platform-specific CPSs. The compiler developed for AIoTML provides a family of code generators to support the construction of digital twins on various heterogeneous target AIoT platforms. Comprehensive evaluations on two complex real-world designs demonstrate the effectiveness of our AIoTML approach in fast development of AIoT-based CPSs with high control quality.