Yongjie Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yongjie Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Xinli Xiong
College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
7 shared publications - Qian Yao
National University of Defense Technology
4 shared publications - Linggang Kong
College of Electronic Engineering, National University of Defense Technology, Hefei, China
3 shared publications Xiaofeng Zhong
3 shared publications- Yang Li
College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
3 shared publications Chungang Gao
National University of Defense Technology, Hefei 230037, China
2 shared publications
Latest Publications
- 5 August 2026
- Published by Elsevier in Information Sciences
- Vol. 758
TrackLGD: Tracking layer-wise graph dynamics for reliable hallucination detection in large language models
- 5 August 2026
- Published by Elsevier in Information Sciences
- Vol. 758
TrackLGD: Tracking layer-wise graph dynamics for reliable hallucination detection in large language models
- Open Access
- 20 March 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (3) , 167
A Multi-Source Feedback-Driven Framework for Generating WAF Test Cases
Web application firewalls (WAFs) are critical defenses against persistent threats to web applications, yet their security evaluation remains challenging. Traditional manual testing methods are often inefficient and resource-intensive, while existing reinforcement learning (RL)-based automated approaches face two key limitations: (1) attackers cannot perceive opaque WAF rule logic; (2) boolean feedback from WAFs results in sparse/delayed rewards—sparse rewards trap agents in blind exploration, and delayed rewards hinder the association between early actions and final outcomes, adversely affecting learning efficiency. To address those challenges, we propose Ouroboros—a framework integrating genetic algorithm-based symbolic rule reconstruction (translating WAF rules into interpretable RNNs for fine-grained confidence scoring), timing side-channel analysis (evaluating rule-matching depth), and a multi-tiered reward mechanism to enable self-evolving RL testing. Experiments show that the framework reaches 89.2% bypass success rate on signature-based WAFs. This paper presents an efficient solution for automated WAF testing and delivers insights for optimizing rule logic and anomaly detection mechanisms.
- 20 March 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (3) , 167
Open AccessA Multi-Source Feedback-Driven Framework for Generating WAF Test Cases
Web application firewalls (WAFs) are critical defenses against persistent threats to web applications, yet their security evaluation remains challenging. Traditional manual testing methods are often inefficient and resource-intensive, while existing reinforcement learning (RL)-based automated approaches face two key limitations: (1) attackers cannot perceive opaque WAF rule logic; (2) boolean feedback from WAFs results in sparse/delayed rewards—sparse rewards trap agents in blind exploration, and delayed rewards hinder the association between early actions and final outcomes, adversely affecting learning efficiency. To address those challenges, we propose Ouroboros—a framework integrating genetic algorithm-based symbolic rule reconstruction (translating WAF rules into interpretable RNNs for fine-grained confidence scoring), timing side-channel analysis (evaluating rule-matching depth), and a multi-tiered reward mechanism to enable self-evolving RL testing. Experiments show that the framework reaches 89.2% bypass success rate on signature-based WAFs. This paper presents an efficient solution for automated WAF testing and delivers insights for optimizing rule logic and anomaly detection mechanisms.
- Open Access
- 23 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (3) , 405
A Meaningful (n, n)-Threshold Visual Secret Sharing Scheme Based on QR Codes and Information Hiding
Visual secret sharing (VSS) schemes can enhance the security of image transmission over networks. Conventional VSS schemes often generate meaningless shares, which can raise suspicion among potential attackers. To address this issue, this paper proposes a novel VSS scheme that integrates information hiding techniques with quick response (QR) codes to generate meaningful shares. The first shares are encoded as standard QR codes, while the n-th share is embedded into a grayscale carrier image using a reversible information hiding method, ensuring the carrier remains visually meaningful. During transmission, the QR codes and the hidden image are distributed. At the receiver end, the hidden n-th share is extracted losslessly from the carrier image using the QR codes, and the original secret image is perfectly reconstructed by bitwise XORing all n shares. Experimental results demonstrate the feasibility, security, and visual quality of the proposed scheme.- 23 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (3) , 405
Open AccessA Meaningful (n, n)-Threshold Visual Secret Sharing Scheme Based on QR Codes and Information Hiding
Visual secret sharing (VSS) schemes can enhance the security of image transmission over networks. Conventional VSS schemes often generate meaningless shares, which can raise suspicion among potential attackers. To address this issue, this paper proposes a novel VSS scheme that integrates information hiding techniques with quick response (QR) codes to generate meaningful shares. The first shares are encoded as standard QR codes, while the n-th share is embedded into a grayscale carrier image using a reversible information hiding method, ensuring the carrier remains visually meaningful. During transmission, the QR codes and the hidden image are distributed. At the receiver end, the hidden n-th share is extracted losslessly from the carrier image using the QR codes, and the original secret image is perfectly reconstructed by bitwise XORing all n shares. Experimental results demonstrate the feasibility, security, and visual quality of the proposed scheme. - 25 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 306
HaluGNN: Hallucination detection in large language models using graph neural network
- 25 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 306
HaluGNN: Hallucination detection in large language models using graph neural network
- 24 November 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (11) , 2298-2309
Multi-perspective consistency checking for large language model hallucination detection: a black-box zero-resource approach
Large language models (LLMs) have been applied across various domains due to their superior natural language processing and generation capabilities. Noneth
- 24 November 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (11) , 2298-2309
Multi-perspective consistency checking for large language model hallucination detection: a black-box zero-resource approach
Large language models (LLMs) have been applied across various domains due to their superior natural language processing and generation capabilities. Noneth
- Open Access
A Novel Framework for Enhancing Decision-Making in Autonomous Cyber Defense Through Graph Embedding
Faced with challenges posed by sophisticated cyber attacks and dynamic characteristics of cyberspace, the autonomous cyber defense (ACD) technology has shown its effectiveness. However, traditional decision-making methods for ACD are unable to effectively characterize the network topology and internode dependencies, which makes it difficult for defenders to identify key nodes and critical attack paths. Therefore, this paper proposes an enhanced decision-making method combining graph embedding with reinforcement learning algorithms. By constructing a game model for cyber confrontations, this paper models important elements of the network topology for decision-making, which guide the defender to dynamically optimize its strategy based on topology awareness. We improve the reinforcement learning with the Node2vec algorithm to characterize information for the defender from the network. And, node attributes and network structural features are embedded into low-dimensional vectors instead of using traditional one-hot encoding, which can address the perceptual bottleneck in high-dimensional sparse environments. Meanwhile, the algorithm training environment Cyberwheel is extended by adding new fine-grained defense mechanisms to enhance the utility and portability of ACD. In experiments, our decision-making method based on graph embedding is compared and analyzed with traditional perception methods. The results show and verify the superior performance of our approach in the strategy selection of defensive decision-making. Also, diverse parameters of the graph representation model Node2vec are analyzed and compared to find the impact on the enhancement of the embedding effectiveness for the decision-making of ACD.
Open AccessA Novel Framework for Enhancing Decision-Making in Autonomous Cyber Defense Through Graph Embedding
Faced with challenges posed by sophisticated cyber attacks and dynamic characteristics of cyberspace, the autonomous cyber defense (ACD) technology has shown its effectiveness. However, traditional decision-making methods for ACD are unable to effectively characterize the network topology and internode dependencies, which makes it difficult for defenders to identify key nodes and critical attack paths. Therefore, this paper proposes an enhanced decision-making method combining graph embedding with reinforcement learning algorithms. By constructing a game model for cyber confrontations, this paper models important elements of the network topology for decision-making, which guide the defender to dynamically optimize its strategy based on topology awareness. We improve the reinforcement learning with the Node2vec algorithm to characterize information for the defender from the network. And, node attributes and network structural features are embedded into low-dimensional vectors instead of using traditional one-hot encoding, which can address the perceptual bottleneck in high-dimensional sparse environments. Meanwhile, the algorithm training environment Cyberwheel is extended by adding new fine-grained defense mechanisms to enhance the utility and portability of ACD. In experiments, our decision-making method based on graph embedding is compared and analyzed with traditional perception methods. The results show and verify the superior performance of our approach in the strategy selection of defensive decision-making. Also, diverse parameters of the graph representation model Node2vec are analyzed and compared to find the impact on the enhancement of the embedding effectiveness for the decision-making of ACD.
- 23 February 2024
- Published by Springer Nature
- p. 57-78
Defeating the Non-stationary Opponent Using Deep Reinforcement Learning and Opponent Modeling
- 23 February 2024
- Published by Springer Nature
- p. 57-78
Defeating the Non-stationary Opponent Using Deep Reinforcement Learning and Opponent Modeling
- 15 December 2023
- Published by Springer Nature
- p. 368-384
Cheat-FlipIt: An Approach to Modeling and Perception of a Deceptive Opponent
- 15 December 2023
- Published by Springer Nature
- p. 368-384
Cheat-FlipIt: An Approach to Modeling and Perception of a Deceptive Opponent
- Open Access
Adversarial Decision-Making for Moving Target Defense: A Multi-Agent Markov Game and Reinforcement Learning Approach
Reinforcement learning has shown a great ability and has defeated human beings in the field of real-time strategy games. In recent years, reinforcement learning has been used in cyberspace to carry out automated and intelligent attacks. Traditional defense methods are not enough to deal with this problem, so it is necessary to design defense agents to counter intelligent attacks. The interaction between the attack agent and the defense agent can be modeled as a multi-agent Markov game. In this paper, an adversarial decision-making approach that combines the Bayesian Strong Stackelberg and the WoLF algorithms was proposed to obtain the equilibrium point of multi-agent Markov games. With this method, the defense agent can obtain the adversarial decision-making strategy as well as continuously adjust the strategy in cyberspace. As verified in experiments, the defense agent should attach importance to short-term rewards in the process of a real-time game between the attack agent and the defense agent. The proposed approach can obtain the largest rewards for defense agent compared with the classic Nash-Q and URS-Q algorithms. In addition, the proposed approach adjusts the action selection probability dynamically, so that the decision entropy of optimal action gradually decreases.
Open AccessAdversarial Decision-Making for Moving Target Defense: A Multi-Agent Markov Game and Reinforcement Learning Approach
Reinforcement learning has shown a great ability and has defeated human beings in the field of real-time strategy games. In recent years, reinforcement learning has been used in cyberspace to carry out automated and intelligent attacks. Traditional defense methods are not enough to deal with this problem, so it is necessary to design defense agents to counter intelligent attacks. The interaction between the attack agent and the defense agent can be modeled as a multi-agent Markov game. In this paper, an adversarial decision-making approach that combines the Bayesian Strong Stackelberg and the WoLF algorithms was proposed to obtain the equilibrium point of multi-agent Markov games. With this method, the defense agent can obtain the adversarial decision-making strategy as well as continuously adjust the strategy in cyberspace. As verified in experiments, the defense agent should attach importance to short-term rewards in the process of a real-time game between the attack agent and the defense agent. The proposed approach can obtain the largest rewards for defense agent compared with the classic Nash-Q and URS-Q algorithms. In addition, the proposed approach adjusts the action selection probability dynamically, so that the decision entropy of optimal action gradually decreases.
- Open Access
- 9 December 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (24) , 12644
FF-MR: A DoH-Encrypted DNS Covert Channel Detection Method Based on Feature Fusion
In this paper, in order to accurately detect Domain Name System (DNS) covert channels based on DNS over HTTPS (DoH) encryption and to solve the problems of weak single-feature differentiation and poor performance in the existing detection methods, we have designed a DoH-encrypted DNS covert channel detection method based on features fusion, called FF-MR. FF-MR is based on a Multi-Head Attention and Residual Neural Network. It fuses session statistical features with multi-channel session byte sequence features. Some important features that play a key role in the detection task are screened out of the fused features through the calculation of the Multi-Head Attention mechanism. Finally, a Multi-Layer Perceptron (MLP) is used to detect encrypted DNS covert channels. By considering both global and focused features, the main idea of FF-MR is that the degree of correlation between each feature and all other features is expressed as an attention weight. Thus, features are re-represented as the result of the weighted fusion of all features using the Multi-Head Attention mechanism. Focusing on certain important features according to the distribution of attention weights improves the detection performance. While detecting the traffic in encrypted DNS covert channels, FF-MR can also accurately identify encrypted traffic generated by the three DNS covert channel tools. Experiments on the CIRA-CIC-DoHBrw-2020 dataset show that the macro-averaging recall and precision of the FF-MR method reach 99.73% and 99.72%, respectively, and the macro-averaging F1-Score reached 0.9978, which is up to 4.56% higher than the existing methods compared in the paper. FF-MR achieves at most an 11.32% improvement in macro-averaging F1-Score in identifying three encrypted DNS covert channels, indicating that FF-MR has a strong ability to detect and identify DoH-encrypted DNS covert channels.
- 9 December 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (24) , 12644
Open AccessFF-MR: A DoH-Encrypted DNS Covert Channel Detection Method Based on Feature Fusion
In this paper, in order to accurately detect Domain Name System (DNS) covert channels based on DNS over HTTPS (DoH) encryption and to solve the problems of weak single-feature differentiation and poor performance in the existing detection methods, we have designed a DoH-encrypted DNS covert channel detection method based on features fusion, called FF-MR. FF-MR is based on a Multi-Head Attention and Residual Neural Network. It fuses session statistical features with multi-channel session byte sequence features. Some important features that play a key role in the detection task are screened out of the fused features through the calculation of the Multi-Head Attention mechanism. Finally, a Multi-Layer Perceptron (MLP) is used to detect encrypted DNS covert channels. By considering both global and focused features, the main idea of FF-MR is that the degree of correlation between each feature and all other features is expressed as an attention weight. Thus, features are re-represented as the result of the weighted fusion of all features using the Multi-Head Attention mechanism. Focusing on certain important features according to the distribution of attention weights improves the detection performance. While detecting the traffic in encrypted DNS covert channels, FF-MR can also accurately identify encrypted traffic generated by the three DNS covert channel tools. Experiments on the CIRA-CIC-DoHBrw-2020 dataset show that the macro-averaging recall and precision of the FF-MR method reach 99.73% and 99.72%, respectively, and the macro-averaging F1-Score reached 0.9978, which is up to 4.56% higher than the existing methods compared in the paper. FF-MR achieves at most an 11.32% improvement in macro-averaging F1-Score in identifying three encrypted DNS covert channels, indicating that FF-MR has a strong ability to detect and identify DoH-encrypted DNS covert channels.