Guozhu Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Guozhu Meng has a total of 164 co-authors. Here are the top co-authors by number of shared publications:
- Kai Chen
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
12 shared publications - Yang Liu
Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Kunming Medical University, China
11 shared publications Kai Chen
SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
4 shared publications- Shangqing Liu
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
3 shared publications Xiaofei Xie
Singapore Management University, Singapore
3 shared publications- Xiaofei Xie
Singapore Management University, Singapore, Singapore
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5582-5596
Implementation Bugs as Attacks: Adversarial Neuron Fuzzing and Supply-Chain Backdoors
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5582-5596
Open AccessImplementation Bugs as Attacks: Adversarial Neuron Fuzzing and Supply-Chain Backdoors
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 11308-11325
The Last Mile of Fuzzing: An Efficient Fault Localization Framework for ARM Embedded Firmware
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 11308-11325
The Last Mile of Fuzzing: An Efficient Fault Localization Framework for ARM Embedded Firmware
- Open Access
- 27 April 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1)
SwitchNet: protecting neural networks by structure obfuscation and switch-controlled inference
Training deep learning models requires substantial financial and human resources, so once deployed in untrusted environments, these models immediately attract the attention of attackers who seek to steal and misuse them. Traditional model protection methods are ineffective in addressing model accuracy, performance, and proactive defense. To this end, we present an active defensive approach SwitchNet by obfuscating model structure and proposing a switch-controlled mechanism to manage model inference. Specifically, SwitchNet learns the weight distribution of the original model and then constructs confusion layers that are strategically inserted into the original model for structure obfuscation. Each of the model layers is equipped with a switch , which is controlled by a switching policy network. We train this policy network with an adaptive pattern as a “secret key” that can accurately control the switch states, and thereby the model inference process. We conduct a comprehensive theoretical analysis of the perturbation boundary and certify that SwitchNet maintains high robustness under $$\ell _\infty$$ perturbations, with certified accuracy exceeding 80% at $$\epsilon = 0.0048$$ (CROWN). In addition, we perform extensive experiments on both classical convolutional networks and Vision Transformers. The results show that SwitchNet effectively preserves model accuracy for legitimate users (with only a 0.35% drop), while reducing the accuracy for unauthorized users to near-random guessing. Compared to the state-of-the-art, our approach reduces inference and construction overhead by 20.89% and 12.08%, respectively. Furthermore, SwitchNet proves to be stealthy and resilient against various attacks aimed at detecting or compromising the protection mechanism.- 27 April 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1)
Open AccessSwitchNet: protecting neural networks by structure obfuscation and switch-controlled inference
Training deep learning models requires substantial financial and human resources, so once deployed in untrusted environments, these models immediately attract the attention of attackers who seek to steal and misuse them. Traditional model protection methods are ineffective in addressing model accuracy, performance, and proactive defense. To this end, we present an active defensive approach SwitchNet by obfuscating model structure and proposing a switch-controlled mechanism to manage model inference. Specifically, SwitchNet learns the weight distribution of the original model and then constructs confusion layers that are strategically inserted into the original model for structure obfuscation. Each of the model layers is equipped with a switch , which is controlled by a switching policy network. We train this policy network with an adaptive pattern as a “secret key” that can accurately control the switch states, and thereby the model inference process. We conduct a comprehensive theoretical analysis of the perturbation boundary and certify that SwitchNet maintains high robustness under $$\ell _\infty$$ perturbations, with certified accuracy exceeding 80% at $$\epsilon = 0.0048$$ (CROWN). In addition, we perform extensive experiments on both classical convolutional networks and Vision Transformers. The results show that SwitchNet effectively preserves model accuracy for legitimate users (with only a 0.35% drop), while reducing the accuracy for unauthorized users to near-random guessing. Compared to the state-of-the-art, our approach reduces inference and construction overhead by 20.89% and 12.08%, respectively. Furthermore, SwitchNet proves to be stealthy and resilient against various attacks aimed at detecting or compromising the protection mechanism. - Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1404-1413
SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1404-1413
Open AccessSAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
- Open Access
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 24-35
Measuring and Explaining the Effects of Android App Transformations in Online Malware Detection
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 24-35
Open AccessMeasuring and Explaining the Effects of Android App Transformations in Online Malware Detection
- Open Access
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 2665-2688
Recasting Type Hints from WebAssembly Contracts
WebAssembly has become the preferred smart contract format for various blockchain platforms due to its high portability and near-native execution speed. To effectively understand WebAssembly contracts, it is crucial to recover high-level type signatures because of the limited type information that WebAssembly provides. However, existing studies on type inference for smart contracts primarily center around Ethereum Virtual Machine bytecode, which is not applicable to WebAssembly owing to their differing targets and runtime semantics. This paper introduces WasmHint, a novel solution that leverages deep learning inference to automatically recover high-level parameter and return types from WebAssembly contracts. More specifically, WasmHint constructs a wCFG representation to clarify dependencies within WebAssembly code and simulates its execution to capture type-related operational information. By learning comprehensive code semantics, it infers parameter and return types, with a semantic corrector designed to enhance information coordination. We conduct experiments on a newly constructed dataset containing 77,208 WebAssembly contract functions. The results demonstrate that WasmHint achieves inference accuracies of 80.0% for parameter types and 95.8% for return types, with average improvements of 86.6% and 34.0% over the baseline methods, respectively.
- 19 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 2 (FSE) , 2665-2688
Open AccessRecasting Type Hints from WebAssembly Contracts
WebAssembly has become the preferred smart contract format for various blockchain platforms due to its high portability and near-native execution speed. To effectively understand WebAssembly contracts, it is crucial to recover high-level type signatures because of the limited type information that WebAssembly provides. However, existing studies on type inference for smart contracts primarily center around Ethereum Virtual Machine bytecode, which is not applicable to WebAssembly owing to their differing targets and runtime semantics. This paper introduces WasmHint, a novel solution that leverages deep learning inference to automatically recover high-level parameter and return types from WebAssembly contracts. More specifically, WasmHint constructs a wCFG representation to clarify dependencies within WebAssembly code and simulates its execution to capture type-related operational information. By learning comprehensive code semantics, it infers parameter and return types, with a semantic corrector designed to enhance information coordination. We conduct experiments on a newly constructed dataset containing 77,208 WebAssembly contract functions. The results demonstrate that WasmHint achieves inference accuracies of 80.0% for parameter types and 95.8% for return types, with average improvements of 86.6% and 34.0% over the baseline methods, respectively.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (5) , 5060-5076
MalFocus: Locating Malicious Modules in Malware Based on Hybrid Deep Learning
In recent years, binary malware detection has attracted extensive attention from industry and academia. However, most of the existing work only focuses on judging whether a sample is malicious or not, rather than identifying malicious modules in malware. Few studies aiming at locating malicious code work on the function granularity and suffer from inaccuracy. In this paper, we address this problem by locating malicious code at the functional module (FM) granularity, which combines several functions to express the malicious behaviors of malware. We design a tool called MalFocus to automatically divide malware into FMs and then identify the malicious functional module (MFM) in a multi-model hybrid manner, in which an unsupervised model and an interpretability approach based on a binary classifier are combined, eliminating the workload of labeling malware samples, determining the scope of MFMs and ranking them according to their maliciousness. The identified MFMs are then passed to security analysts for verification, helping to significantly reduce the scope of manual analysis while providing a comprehensive view of the malware attack flow. Additionally, rules derived from the verified MFMs can be used to detect variants and new malware families with different functionalities, offering a more general and flexible detection approach. We evaluate MalFocus’s performance on 6764 real-world samples. The results show that MalFocus can correctly identify 95% of MFMs, outperforming current state-of-the-art work.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (5) , 5060-5076
MalFocus: Locating Malicious Modules in Malware Based on Hybrid Deep Learning
In recent years, binary malware detection has attracted extensive attention from industry and academia. However, most of the existing work only focuses on judging whether a sample is malicious or not, rather than identifying malicious modules in malware. Few studies aiming at locating malicious code work on the function granularity and suffer from inaccuracy. In this paper, we address this problem by locating malicious code at the functional module (FM) granularity, which combines several functions to express the malicious behaviors of malware. We design a tool called MalFocus to automatically divide malware into FMs and then identify the malicious functional module (MFM) in a multi-model hybrid manner, in which an unsupervised model and an interpretability approach based on a binary classifier are combined, eliminating the workload of labeling malware samples, determining the scope of MFMs and ranking them according to their maliciousness. The identified MFMs are then passed to security analysts for verification, helping to significantly reduce the scope of manual analysis while providing a comprehensive view of the malware attack flow. Additionally, rules derived from the verified MFMs can be used to detect variants and new malware families with different functionalities, offering a more general and flexible detection approach. We evaluate MalFocus’s performance on 6764 real-world samples. The results show that MalFocus can correctly identify 95% of MFMs, outperforming current state-of-the-art work.
- 4 March 2025
- Published by Springer Nature
- p. 295-312
FAF-BM: An Approach for False Alerts Filtering Using BERT Model with Semi-supervised Active Learning
- 4 March 2025
- Published by Springer Nature
- p. 295-312
FAF-BM: An Approach for False Alerts Filtering Using BERT Model with Semi-supervised Active Learning
- Open Access
SAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
Given the need to evaluate the robustness of face recognition (FR) models, many efforts have focused on adversarial patch attacks that mislead FR models by introducing localized perturbations. Impersonation attacks are a significant threat because adversarial perturbations allow attackers to disguise themselves as legitimate users. This can lead to severe consequences, including data breaches, system damage, and misuse of resources. However, research on such attacks in FR remains limited. Existing adversarial patch generation methods exhibit limited efficacy in impersonation attacks due to (1) the need for high attacker capabilities, (2) low attack success rates, and (3) excessive query requirements. To address these challenges, we propose a novel method SAP-DIFF that leverages diffusion models to generate adversarial patches via semantic perturbations in the latent space rather than direct pixel manipulation. We introduce an attention disruption mechanism to generate features unrelated to the original face, facilitating the creation of adversarial samples and a directional loss function to guide perturbations toward the target identity feature space, thereby enhancing attack effectiveness and efficiency. Extensive experiments on popular FR models and datasets demonstrate that our method outperforms state-of-the-art approaches, achieving an average attack success rate improvement of 45.66% (all exceeding 40%), and a reduction in the number of queries by about 40% compared to the SOTA approach
Open AccessSAP-DIFF: Semantic Adversarial Patch Generation for Black-Box Face Recognition Models via Diffusion Models
Given the need to evaluate the robustness of face recognition (FR) models, many efforts have focused on adversarial patch attacks that mislead FR models by introducing localized perturbations. Impersonation attacks are a significant threat because adversarial perturbations allow attackers to disguise themselves as legitimate users. This can lead to severe consequences, including data breaches, system damage, and misuse of resources. However, research on such attacks in FR remains limited. Existing adversarial patch generation methods exhibit limited efficacy in impersonation attacks due to (1) the need for high attacker capabilities, (2) low attack success rates, and (3) excessive query requirements. To address these challenges, we propose a novel method SAP-DIFF that leverages diffusion models to generate adversarial patches via semantic perturbations in the latent space rather than direct pixel manipulation. We introduce an attention disruption mechanism to generate features unrelated to the original face, facilitating the creation of adversarial samples and a directional loss function to guide perturbations toward the target identity feature space, thereby enhancing attack effectiveness and efficiency. Extensive experiments on popular FR models and datasets demonstrate that our method outperforms state-of-the-art approaches, achieving an average attack success rate improvement of 45.66% (all exceeding 40%), and a reduction in the number of queries by about 40% compared to the SOTA approach