Lei Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lei Cui has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Zhiyu Hao
Zhongguancun Laboratory, Beijing, China
11 shared publications Zhiyu Hao
5 shared publications- Junnan Yin
Zhongguancun Laboratory, Beijing, China
3 shared publications Lun Li
3 shared publications- Lun Li
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
3 shared publications Xiaochun Yun
3 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by Elsevier in SSRN Electronic Journal
MGCL: Tor Website Fingerprinting For Reload Scenario
Website fingerprinting (WF) attacks aim to identify the websites being visited by analyzing their characteristics. Although prior studies have demonstrated that WF can compromise Tor’s anonymity, they largely assume clean browsing environments. In practice, however, users often revisit pages or navigate within the same site, creating reload traffics where cached resources introduce significant traffic variations. These variations pose challenges to traditional WF methods, yet this issue has received limited attention to date.In this paper, we propose MGCL, a novel Multi-Granularity Contrastive Learning approach for Tor website fingerprinting in reload scenarios. MGCL leverages multi-granularity spatiotemporal features to provide a more comprehensive and robust representation of traffic patterns, thereby enabling more accurate traffic characterization. Then, a dual-branch neural network architecture is designed to process them separately to accommodate their unique semantics and eventually fuse these features. Furthermore, MGCL incorporates supervised contrastive learning to tackle the challenge of distinguishing reload traffic from first-time visit traffic, which belong to the same class but exhibit markedly different feature distributions. By refining feature representations in the vector space, MGCL enhances the model’s robustness to such discrepancies. Experimental results show that MGCL outperforms the state-of-the-art, achieving an accuracy of 85.83%, which is over 10% higher than existing methods.
- 8 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMGCL: Tor Website Fingerprinting For Reload Scenario
Website fingerprinting (WF) attacks aim to identify the websites being visited by analyzing their characteristics. Although prior studies have demonstrated that WF can compromise Tor’s anonymity, they largely assume clean browsing environments. In practice, however, users often revisit pages or navigate within the same site, creating reload traffics where cached resources introduce significant traffic variations. These variations pose challenges to traditional WF methods, yet this issue has received limited attention to date.In this paper, we propose MGCL, a novel Multi-Granularity Contrastive Learning approach for Tor website fingerprinting in reload scenarios. MGCL leverages multi-granularity spatiotemporal features to provide a more comprehensive and robust representation of traffic patterns, thereby enabling more accurate traffic characterization. Then, a dual-branch neural network architecture is designed to process them separately to accommodate their unique semantics and eventually fuse these features. Furthermore, MGCL incorporates supervised contrastive learning to tackle the challenge of distinguishing reload traffic from first-time visit traffic, which belong to the same class but exhibit markedly different feature distributions. By refining feature representations in the vector space, MGCL enhances the model’s robustness to such discrepancies. Experimental results show that MGCL outperforms the state-of-the-art, achieving an accuracy of 85.83%, which is over 10% higher than existing methods.
- 25 June 2026
- Published by Elsevier in Information and Software Technology
- Vol. 198
API2TA: Learning tactic-aware representations of APIs for malware detection, classification and understanding
- 25 June 2026
- Published by Elsevier in Information and Software Technology
- Vol. 198
API2TA: Learning tactic-aware representations of APIs for malware detection, classification and understanding
- Open Access
- 13 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35  (6) , 1-31
PVDetector: Pretrained Vulnerability Detection on Vulnerability-enriched Code Semantic Graph
Automated vulnerability detection is a critical issue in software security. The advent of Deep Learning (DL) has led to numerous studies employing DL to detect vulnerabilities in software source code. However, existing approaches still perform poorly, particularly with real-world vulnerabilities, due to the difficulty in accurately capturing their properties. To this end, we introduce PVDetector, a DL-based approach that utilizes rich code semantics, incorporates vulnerability knowledge, and leverages pretrained code representations for precise vulnerability detection. At its core, PVDetector employs a new model called Vulnerability-enriched Code Semantic Graph (VCSG), which accurately characterizes functions by distinguishing the semantics of identical variables and more finely capturing control dependencies, data dependencies, and vulnerability relationships. Additionally, we introduce four pretraining tasks specifically designed to learn the semantics of control, data, vulnerability, and variables from the VCSG model. These pretraining tasks significantly enhance PVDetector’s capability to detect vulnerabilities in downstream tasks. Experimental results indicate that PVDetector outperforms SOTAs by 5.0–12.5% in precision, 0.2–9.7% in recall, and 3.0–15.1% in F1-score. Additionally, it supports six programming languages and demonstrates high efficiency (e.g., 10.6 \(\times\) faster than DeepDFA). When applied to seven software products, PVDetector discovered 55 vulnerabilities, including 10 silently patched flaws that had not been previously reported.- 13 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35  (6) , 1-31
Open AccessPVDetector: Pretrained Vulnerability Detection on Vulnerability-enriched Code Semantic Graph
Automated vulnerability detection is a critical issue in software security. The advent of Deep Learning (DL) has led to numerous studies employing DL to detect vulnerabilities in software source code. However, existing approaches still perform poorly, particularly with real-world vulnerabilities, due to the difficulty in accurately capturing their properties. To this end, we introduce PVDetector, a DL-based approach that utilizes rich code semantics, incorporates vulnerability knowledge, and leverages pretrained code representations for precise vulnerability detection. At its core, PVDetector employs a new model called Vulnerability-enriched Code Semantic Graph (VCSG), which accurately characterizes functions by distinguishing the semantics of identical variables and more finely capturing control dependencies, data dependencies, and vulnerability relationships. Additionally, we introduce four pretraining tasks specifically designed to learn the semantics of control, data, vulnerability, and variables from the VCSG model. These pretraining tasks significantly enhance PVDetector’s capability to detect vulnerabilities in downstream tasks. Experimental results indicate that PVDetector outperforms SOTAs by 5.0–12.5% in precision, 0.2–9.7% in recall, and 3.0–15.1% in F1-score. Additionally, it supports six programming languages and demonstrates high efficiency (e.g., 10.6 \(\times\) faster than DeepDFA). When applied to seven software products, PVDetector discovered 55 vulnerabilities, including 10 silently patched flaws that had not been previously reported. - Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 135-145
Modubin: A Binary Modularization Approach Based on the Locality of Homologous Functions
Complex software systems are typically built from multiple functional modules, which serve as both structural units for implementing specific functionalities and the actual granularity for third-party library (TPL) reuse. Consequently, recovering high-quality modular structures from binaries becomes essential for advancing program comprehension and TPL reuse detection. However, this valuable modular structure is lost during compilation, making it unavailable for direct extraction from binaries. While existing community detection-based binary modularization methods can extract modules, they suffer from poor scalability when processing large binaries and produce inconsistently sized modules across binaries of varying scales. To address these limitations, we propose Modubin, an efficient binary modularization approach based on the locality of homologous functions. Our method leverages their call cohesion through a three-phase pipeline: Local Aggregation segments function intervals based on address ordering and locally aggregates homologous functions into function clusters; Module Growth progressively merges adjacent fragmented edges into stable module backbones to form initial module prototypes; Module Merging refines the results based on inter-module call coupling strength to produce final modules. Experimental results demonstrate that Modubin achieves remarkable efficiency improvements, reducing average processing time by 96.9% to just 5.18 seconds per binary while exhibiting near O(n) time complexity. Meanwhile, it improves modularization quality by 6.89% across six evaluation metrics and shows stronger stability in practical TPL reuse detection scenarios.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 135-145
Open AccessModubin: A Binary Modularization Approach Based on the Locality of Homologous Functions
Complex software systems are typically built from multiple functional modules, which serve as both structural units for implementing specific functionalities and the actual granularity for third-party library (TPL) reuse. Consequently, recovering high-quality modular structures from binaries becomes essential for advancing program comprehension and TPL reuse detection. However, this valuable modular structure is lost during compilation, making it unavailable for direct extraction from binaries. While existing community detection-based binary modularization methods can extract modules, they suffer from poor scalability when processing large binaries and produce inconsistently sized modules across binaries of varying scales. To address these limitations, we propose Modubin, an efficient binary modularization approach based on the locality of homologous functions. Our method leverages their call cohesion through a three-phase pipeline: Local Aggregation segments function intervals based on address ordering and locally aggregates homologous functions into function clusters; Module Growth progressively merges adjacent fragmented edges into stable module backbones to form initial module prototypes; Module Merging refines the results based on inter-module call coupling strength to produce final modules. Experimental results demonstrate that Modubin achieves remarkable efficiency improvements, reducing average processing time by 96.9% to just 5.18 seconds per binary while exhibiting near O(n) time complexity. Meanwhile, it improves modularization quality by 6.89% across six evaluation metrics and shows stronger stability in practical TPL reuse detection scenarios.
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1235-1250
TaintEMU: Decoupling Tracking from Functional Domains for Architecture-Agnostic and Efficient Whole-System Taint Tracking
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1235-1250
Open AccessTaintEMU: Decoupling Tracking from Functional Domains for Architecture-Agnostic and Efficient Whole-System Taint Tracking
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20  (15566013) , 1794-1806
Bottom Aggregating, Top Separating: An Aggregator and Separator Network for Encrypted Traffic Understanding
Encrypted traffic classification refers to the task of identifying the application, service or malware associated with network traffic that is encrypted. Previous methods mainly have two weaknesses. Firstly, from the perspective of word-level (namely, byte-level) semantics, current methods use pre-training language models like BERT, learned general natural language knowledge, to directly process byte-based traffic data. However, understanding traffic data is different from understanding words in natural language, using BERT directly on traffic data could disrupt internal word sense information so as to affect the performance of classification. Secondly, from the perspective of packet-level semantics, current methods mostly implicitly classify traffic using abstractive semantic features learned at the top layer, without further explicitly separating the features into different space of categories, leading to poor feature discriminability. In this paper, we propose a simple but effective Aggregator and Separator Network (ASNet) for encrypted traffic understanding, which consists of two core modules. Specifically, a parameter-free word sense aggregator enables BERT to rapidly adapt to understanding traffic data and keeping the complete word sense without introducing additional model parameters. And a category-constrained semantics separator with task-aware prompts (as the stimulus) is introduced to explicitly conduct feature learning independently in semantic spaces of different categories. Experiments on five datasets across seven tasks demonstrate that our proposed model achieves the current state-of-the-art results without pre-training in both the public benchmark and real-world collected traffic dataset. Statistical analyses and visualization experiments also validate the interpretability of the core modules. Furthermore, what is important is that ASNet does not need pre-training, which dramatically reduces the cost of computing power and time. The model code and dataset will be released in https://github.com/pengwei-iie/ASNET.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20  (15566013) , 1794-1806
Bottom Aggregating, Top Separating: An Aggregator and Separator Network for Encrypted Traffic Understanding
Encrypted traffic classification refers to the task of identifying the application, service or malware associated with network traffic that is encrypted. Previous methods mainly have two weaknesses. Firstly, from the perspective of word-level (namely, byte-level) semantics, current methods use pre-training language models like BERT, learned general natural language knowledge, to directly process byte-based traffic data. However, understanding traffic data is different from understanding words in natural language, using BERT directly on traffic data could disrupt internal word sense information so as to affect the performance of classification. Secondly, from the perspective of packet-level semantics, current methods mostly implicitly classify traffic using abstractive semantic features learned at the top layer, without further explicitly separating the features into different space of categories, leading to poor feature discriminability. In this paper, we propose a simple but effective Aggregator and Separator Network (ASNet) for encrypted traffic understanding, which consists of two core modules. Specifically, a parameter-free word sense aggregator enables BERT to rapidly adapt to understanding traffic data and keeping the complete word sense without introducing additional model parameters. And a category-constrained semantics separator with task-aware prompts (as the stimulus) is introduced to explicitly conduct feature learning independently in semantic spaces of different categories. Experiments on five datasets across seven tasks demonstrate that our proposed model achieves the current state-of-the-art results without pre-training in both the public benchmark and real-world collected traffic dataset. Statistical analyses and visualization experiments also validate the interpretability of the core modules. Furthermore, what is important is that ASNet does not need pre-training, which dramatically reduces the cost of computing power and time. The model code and dataset will be released in https://github.com/pengwei-iie/ASNET.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50  (8) , 2142-2162
API2Vec++: Boosting API Sequence Representation for Malware Detection and Classification
Analyzing malware based on API call sequences is an effective approach, as these sequences reflect the dynamic execution behavior of malware. Recent advancements in deep learning have facilitated the application of these techniques to mine valuable information from API call sequences. However, these methods typically operate on raw sequences and may not effectively capture crucial information, especially in the case of multi-process malware, due to the API call interleaving problem . Furthermore, they often fail to capture contextual behaviors within or across processes, which is particularly important for identifying and classifying malicious activities. Motivated by this, we present API2Vec++, a graph-based API embedding method for malware detection and classification. First, we construct a graph model to represent the raw sequence. Specifically, we design the Temporal Process Graph (TPG) to model inter-process behaviors and the Temporal API Property Graph (TAPG) to model intra-process behaviors. Compared to our previous graph model, the TAPG model exposes operations with associated behaviors within the process through node properties and thus enhances detection and classification abilities. Using these graphs, we develop a heuristic random walk algorithm to generate numerous paths that can capture fine-grained malicious familial behavior. By pre-training these paths using the BERT model, we generate embeddings of paths and APIs, which can then be used for malware detection and classification. Experiments on a real-world malware dataset demonstrate that API2Vec++ outperforms state-of-the-art embedding methods and detection/classification methods in both accuracy and robustness, particularly for multi-process malware.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50  (8) , 2142-2162
API2Vec++: Boosting API Sequence Representation for Malware Detection and Classification
Analyzing malware based on API call sequences is an effective approach, as these sequences reflect the dynamic execution behavior of malware. Recent advancements in deep learning have facilitated the application of these techniques to mine valuable information from API call sequences. However, these methods typically operate on raw sequences and may not effectively capture crucial information, especially in the case of multi-process malware, due to the API call interleaving problem . Furthermore, they often fail to capture contextual behaviors within or across processes, which is particularly important for identifying and classifying malicious activities. Motivated by this, we present API2Vec++, a graph-based API embedding method for malware detection and classification. First, we construct a graph model to represent the raw sequence. Specifically, we design the Temporal Process Graph (TPG) to model inter-process behaviors and the Temporal API Property Graph (TAPG) to model intra-process behaviors. Compared to our previous graph model, the TAPG model exposes operations with associated behaviors within the process through node properties and thus enhances detection and classification abilities. Using these graphs, we develop a heuristic random walk algorithm to generate numerous paths that can capture fine-grained malicious familial behavior. By pre-training these paths using the BERT model, we generate embeddings of paths and APIs, which can then be used for malware detection and classification. Experiments on a real-world malware dataset demonstrate that API2Vec++ outperforms state-of-the-art embedding methods and detection/classification methods in both accuracy and robustness, particularly for multi-process malware.
- 22 January 2024
- Published by Elsevier in Computers & Security
- Vol. 139, 103732
VDTriplet: Vulnerability detection with graph semantics using triplet model
- 22 January 2024
- Published by Elsevier in Computers & Security
- Vol. 139, 103732
VDTriplet: Vulnerability detection with graph semantics using triplet model
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 34  (8) , 2433-2447
eHotSnap: An Efficient and Hot Distributed Snapshots System for Virtual Machine Cluster
With the popularity of IaaS clouds, many distributed and networked applications are running in virtual machine cluster (VMC). The distributed snapshots of VMC are a practical approach to guarantee system reliability. It rewinds the system to an intermediate state from failures so that the applications can continue execution from a point near the failure. However, the applications running in the VMC suffer from long disruption and significant performance degradation due to the heavy cost distributed snapshots, especially when designed to guarantee global consistency of VMC snapshots. This article presents eHotSnap, which takes distributed snapshots of a VMC efficiently. eHotSnap divides the native snapshot into light cost transient snapshot and heavy cost memory snapshot and then coordinates the VM snapshots immediately after transient snapshots. In this way, it decouples coordination from heavy cost snapshots so that the distributed snapshots are taken (completed in logic) within a second. Then, it performs memory snapshot and optimizes it with a two-layer optimization, which first employs de-duplication to reduce the amount of snapshot data and then leverages priority queue to serve guest write operations preferentially. In addition to presenting eHotSnap, we have implemented a prototype on QEMU/KVM. The experimental results demonstrate the effectiveness and efficiency of the proposed approach.
- 1 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 34  (8) , 2433-2447
eHotSnap: An Efficient and Hot Distributed Snapshots System for Virtual Machine Cluster
With the popularity of IaaS clouds, many distributed and networked applications are running in virtual machine cluster (VMC). The distributed snapshots of VMC are a practical approach to guarantee system reliability. It rewinds the system to an intermediate state from failures so that the applications can continue execution from a point near the failure. However, the applications running in the VMC suffer from long disruption and significant performance degradation due to the heavy cost distributed snapshots, especially when designed to guarantee global consistency of VMC snapshots. This article presents eHotSnap, which takes distributed snapshots of a VMC efficiently. eHotSnap divides the native snapshot into light cost transient snapshot and heavy cost memory snapshot and then coordinates the VM snapshots immediately after transient snapshots. In this way, it decouples coordination from heavy cost snapshots so that the distributed snapshots are taken (completed in logic) within a second. Then, it performs memory snapshot and optimizes it with a two-layer optimization, which first employs de-duplication to reduce the amount of snapshot data and then leverages priority queue to serve guest write operations preferentially. In addition to presenting eHotSnap, we have implemented a prototype on QEMU/KVM. The experimental results demonstrate the effectiveness and efficiency of the proposed approach.
- 11 January 2023
- Published by Springer Nature
- p. 98-116
SeqTrace: API Call Tracing Based on Intel PT and VMI for Malware Detection
- 11 January 2023
- Published by Springer Nature
- p. 98-116
SeqTrace: API Call Tracing Based on Intel PT and VMI for Malware Detection