Lei Zhao
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
Lei Zhao has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Yiru Zhao
Wuhan University
8 shared publications Lina Wang
Wuhan University
4 shared publications- Lina Wang
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China
4 shared publications Wenxin Li
Wuhan University
3 shared publications- Xiaoke Wang
School of Cybersecurity, Tianjin University, Tianjin, China
3 shared publications Yiru Zhao
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1552-1566
ACOFuzz: Memory-Error-Sensitive Fuzzing Driven by Address-Computation-Operand-Aware Feedback Mechanism
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1552-1566
Open AccessACOFuzz: Memory-Error-Sensitive Fuzzing Driven by Address-Computation-Operand-Aware Feedback Mechanism
- 23 October 2026
- Published by Springer Nature
- p. 103-119
Targeted Semantic Subspace Perturbation Against Model Inversion Attacks
- 23 October 2026
- Published by Springer Nature
- p. 103-119
Targeted Semantic Subspace Perturbation Against Model Inversion Attacks
- 23 October 2026
- Published by Springer Nature
- p. 85-101
SCOUT: Structural Coverage-Guided Diffusion for Testing Deep Classifiers
- 23 October 2026
- Published by Springer Nature
- p. 85-101
SCOUT: Structural Coverage-Guided Diffusion for Testing Deep Classifiers
- 18 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Adaptive adversarial interpolation for diffusion-based facial privacy protection
- 18 July 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
Adaptive adversarial interpolation for diffusion-based facial privacy protection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 6083-6098
MicroPatch : Directed Backdoor Erasing via Victim Parameter Decoupling
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 6083-6098
MicroPatch : Directed Backdoor Erasing via Victim Parameter Decoupling
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 3161-3175
When Deepfake Meets Backdoor: Leveraging GAN Fingerprints for Data Poisoning Attack
Deep Neural Networks are vulnerable to data poisoning attacks, which inject a backdoor by poisoning the training data set with a predefined trigger pattern. However, most existing studies design trigger patterns as exogenous features introduced to clean samples (such as a checkerboard patch), whereas the endogenous features inherited from sample origins (such as deep generative models) have not been investigated yet. In this study, we investigate the efficacy of utilizing Generative Adversarial Network fingerprints to design trigger patterns by examining three attack patterns: the all-label attack, label-specific attack, and semantic-specific attack. Specifically, we select training data that satisfies the requirements of various attack patterns, train a GAN model, and employ samples embedded with GAN fingerprints to generate poisoned data sets. Our evaluations on three data sets (CIFAR-10, GTSRB, and LSUN) demonstrate that employing GAN fingerprints as trigger patterns 1) can achieve average attack success rate results of 39.40% in all-label attack, 89.84% in label-specific attack, and 91.06% in semantic-specific attack, 2) is stealthy by reducing the probability of being exposed, and 3) can resist six existing backdoor detection techniques, three backdoor erasing techniques, and two deepfake detection techniques. Furthermore, it exhibits practical applicability in federated learning scenario.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 3161-3175
When Deepfake Meets Backdoor: Leveraging GAN Fingerprints for Data Poisoning Attack
Deep Neural Networks are vulnerable to data poisoning attacks, which inject a backdoor by poisoning the training data set with a predefined trigger pattern. However, most existing studies design trigger patterns as exogenous features introduced to clean samples (such as a checkerboard patch), whereas the endogenous features inherited from sample origins (such as deep generative models) have not been investigated yet. In this study, we investigate the efficacy of utilizing Generative Adversarial Network fingerprints to design trigger patterns by examining three attack patterns: the all-label attack, label-specific attack, and semantic-specific attack. Specifically, we select training data that satisfies the requirements of various attack patterns, train a GAN model, and employ samples embedded with GAN fingerprints to generate poisoned data sets. Our evaluations on three data sets (CIFAR-10, GTSRB, and LSUN) demonstrate that employing GAN fingerprints as trigger patterns 1) can achieve average attack success rate results of 39.40% in all-label attack, 89.84% in label-specific attack, and 91.06% in semantic-specific attack, 2) is stealthy by reducing the probability of being exposed, and 3) can resist six existing backdoor detection techniques, three backdoor erasing techniques, and two deepfake detection techniques. Furthermore, it exhibits practical applicability in federated learning scenario.
- Open Access
- 2 June 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (4) , 1-17
RIMFuzz: real-time impact-aware mutation for library API fuzzing
- 2 June 2025
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 37 (4) , 1-17
Open AccessRIMFuzz: real-time impact-aware mutation for library API fuzzing
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 22 (3) , 2822-2837
ArchSentry: Enhanced Android Malware Detection via Hierarchical Semantic Extraction
Android malware poses a significant challenge for mobile platforms. To evade detection, contemporary malware variants use API substitution or obfuscation techniques to hide malicious activities and mask their shallow semantic characteristics. However, existing research lacks analysis of the hierarchical semantic associated with Android apps. To address this problem, we propose ArchSentry, an enhanced Android malware detection via hierarchical semantic extraction. First, we select entities and their relationships relevant to Android software behavior through the software architecture and represent them using a heterogeneous graph. Then, we structure meta-paths to represent rich semantic information to achieve semantic enhancement and improve efficiency. Next, we design a meta-path semantic selection method based on KL Divergence to identify and eliminate redundant features. To achieve a comprehensive representation of the overall software semantics and improve performance, we construct a feature fusion approach based on Restricted Boltzmann Machines (RBM) and AutoEncoder (AE) during the pre-training phase, while preserving the probability distribution characteristics of various meta-paths. Finally, Deep Neural Networks (DNN) process fusion features for comprehensive feature sets. Experimental results on real-world application samples indicate that ArchSentry achieves a remarkable 99.2% detection rate for Android malware, with a low false positive rate below 1%. These results surpass the performance of current state-of-the-art approaches.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 22 (3) , 2822-2837
ArchSentry: Enhanced Android Malware Detection via Hierarchical Semantic Extraction
Android malware poses a significant challenge for mobile platforms. To evade detection, contemporary malware variants use API substitution or obfuscation techniques to hide malicious activities and mask their shallow semantic characteristics. However, existing research lacks analysis of the hierarchical semantic associated with Android apps. To address this problem, we propose ArchSentry, an enhanced Android malware detection via hierarchical semantic extraction. First, we select entities and their relationships relevant to Android software behavior through the software architecture and represent them using a heterogeneous graph. Then, we structure meta-paths to represent rich semantic information to achieve semantic enhancement and improve efficiency. Next, we design a meta-path semantic selection method based on KL Divergence to identify and eliminate redundant features. To achieve a comprehensive representation of the overall software semantics and improve performance, we construct a feature fusion approach based on Restricted Boltzmann Machines (RBM) and AutoEncoder (AE) during the pre-training phase, while preserving the probability distribution characteristics of various meta-paths. Finally, Deep Neural Networks (DNN) process fusion features for comprehensive feature sets. Experimental results on real-world application samples indicate that ArchSentry achieves a remarkable 99.2% detection rate for Android malware, with a low false positive rate below 1%. These results surpass the performance of current state-of-the-art approaches.
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. PP (15455971) , 1-14
Towards Tightly-coupled Hybrid Fuzzing via Excavating Input Specifications
Hybrid fuzzing, which combines fuzzing and concolic execution based on the observation that these two types of techniques are complementary, has recently become a research focus. Several hybrid fuzzing studies have shown that concolic execution can assist fuzzing in exploring deeper program states and discovering more vulnerabilities. Despite advances in hybrid fuzzing, most existing techniques employ a result-oriented scheme in which fuzzing and concolic execution cooperate by synchronizing generated test cases. Such cooperation underestimates the sophisticated analysis of concolic execution on the program. Based on the observation that concolic execution can generate abundant program states, which are desirable to be investigated for improving the performance of hybrid fuzzing, we propose a tightly-coupled hybrid fuzzing technique by excavating input specifications from concolic execution. Specifically, we define and excavate three input specification types: critical region, critical value, and type inference. We further design new fuzzing mutation algorithms to leverage them to guide the exploration of the program states. We implement three prototypes, Gear-Driller , Gear-DigFuzz and Gear-QSYM , on top of Driller, DigFuzz and QSYM, respectively. Experimental results show that Gear-Driller , Gear-DigFuzz and Gear-QSYM outperform Driller, DigFuzz and QSYM with larger code coverage, more discovered vulnerabilities, and higher efficiency in finding vulnerabilities.
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. PP (15455971) , 1-14
Towards Tightly-coupled Hybrid Fuzzing via Excavating Input Specifications
Hybrid fuzzing, which combines fuzzing and concolic execution based on the observation that these two types of techniques are complementary, has recently become a research focus. Several hybrid fuzzing studies have shown that concolic execution can assist fuzzing in exploring deeper program states and discovering more vulnerabilities. Despite advances in hybrid fuzzing, most existing techniques employ a result-oriented scheme in which fuzzing and concolic execution cooperate by synchronizing generated test cases. Such cooperation underestimates the sophisticated analysis of concolic execution on the program. Based on the observation that concolic execution can generate abundant program states, which are desirable to be investigated for improving the performance of hybrid fuzzing, we propose a tightly-coupled hybrid fuzzing technique by excavating input specifications from concolic execution. Specifically, we define and excavate three input specification types: critical region, critical value, and type inference. We further design new fuzzing mutation algorithms to leverage them to guide the exploration of the program states. We implement three prototypes, Gear-Driller , Gear-DigFuzz and Gear-QSYM , on top of Driller, DigFuzz and QSYM, respectively. Experimental results show that Gear-Driller , Gear-DigFuzz and Gear-QSYM outperform Driller, DigFuzz and QSYM with larger code coverage, more discovered vulnerabilities, and higher efficiency in finding vulnerabilities.
- Open Access
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 934-946
Input-Driven Dynamic Program Debloating for Code-Reuse Attack Mitigation
Modern software is bloated, especially for libraries. The unnecessary code not only brings severe vulnerabilities, but also assists attackers to construct exploits. To mitigate the damage of bloated libraries, researchers have proposed several debloating techniques to remove or restrict the invocation of unused code in a library. However, existing approaches either statically keep code for all expected inputs, which leave unused code for each concrete input, or rely on runtime context to dynamically determine the necessary code, which could be manipulated by attackers. In this paper, we propose Picup, a practical approach that dynamically customizes libraries for each input. Based on the observation that the behavior of a program mainly depends on the given input, we design Picup to predict the necessary library functions immediately after we get the input, which erases the unused code before attackers can affect the decision-making data. To achieve an effective prediction, we adopt a convolutional neural network (CNN) with attention mechanism to extract key bytes from the input and map them to library functions. We evaluate Picup on real-world benchmarks and popular applications. The results show that we can predict the necessary library functions with 97.56% accuracy, and reduce the code size by 87.55% on average with low overheads. These results indicate that Picup is a practical solution for secure and effective library debloating.
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 934-946
Open AccessInput-Driven Dynamic Program Debloating for Code-Reuse Attack Mitigation
Modern software is bloated, especially for libraries. The unnecessary code not only brings severe vulnerabilities, but also assists attackers to construct exploits. To mitigate the damage of bloated libraries, researchers have proposed several debloating techniques to remove or restrict the invocation of unused code in a library. However, existing approaches either statically keep code for all expected inputs, which leave unused code for each concrete input, or rely on runtime context to dynamically determine the necessary code, which could be manipulated by attackers. In this paper, we propose Picup, a practical approach that dynamically customizes libraries for each input. Based on the observation that the behavior of a program mainly depends on the given input, we design Picup to predict the necessary library functions immediately after we get the input, which erases the unused code before attackers can affect the decision-making data. To achieve an effective prediction, we adopt a convolutional neural network (CNN) with attention mechanism to extract key bytes from the input and map them to library functions. We evaluate Picup on real-world benchmarks and popular applications. The results show that we can predict the necessary library functions with 97.56% accuracy, and reduce the code size by 87.55% on average with low overheads. These results indicate that Picup is a practical solution for secure and effective library debloating.