Baoxu Liu
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
Baoxu Liu has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Liangchen Chen
Wuhan University of Technology
5 shared publications - Shu Gao
Wuhan University of Technology
3 shared publications - Zhengwei Jiang
Institute of Information Engineering, Chinese Academy of Sciences
3 shared publications - Zhigang Lu
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
3 shared publications - Bo Jiang
Chinese Academy of Sciences
2 shared publications - Xu-Yao Zhang
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications
Latest Publications
- 26 September 2026
- Published by Springer Nature
- p. 50-64
TransDyG: An Anomaly Detection Method Integrating Dynamic Graphs and Transformers
- 26 September 2026
- Published by Springer Nature
- p. 50-64
TransDyG: An Anomaly Detection Method Integrating Dynamic Graphs and Transformers
- Open Access
- 22 July 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 194
No train, no pain: a training-free few-shot traffic classifier based on LLMs
Encrypted web traffic and evolving Internet technologies pose an increasing challenge to network traffic analysis. However, existing traffic classification methods, though effective, require large labeled datasets and complex training. This makes sustaining them prohibitively expensive and difficult in real-world scenarios. To narrow this gap, we propose a novel training-free few-shot network traffic classification framework based on large language models (LLMs). By integrating meta-learning with LLMs, it reduces reliance on labeled data, eliminates task-specific training, and improves performance. Specifically, we first apply an efficient feature extraction method to extract features from traffic flows. We then design meta-tasks that combine task descriptions with textualized features to produce natural language meta-task formulations. Building on these meta-tasks, the LLM performs reasoning to carry out traffic classification. Finally, to mitigate hallucination in the LLM outputs, we exploit the temporal characteristics of network traffic and aggregate predictions over samples within a defined time window. Extensive experiments on three widely-used encrypted traffic datasets demonstrate that our proposed framework outperforms the state-of-the-art methods, achieving an average absolute improvement in F1 score of 9.75, 9.82, and 12.06 percentage points on the three datasets, respectively.
- 22 July 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 194
Open AccessNo train, no pain: a training-free few-shot traffic classifier based on LLMs
Encrypted web traffic and evolving Internet technologies pose an increasing challenge to network traffic analysis. However, existing traffic classification methods, though effective, require large labeled datasets and complex training. This makes sustaining them prohibitively expensive and difficult in real-world scenarios. To narrow this gap, we propose a novel training-free few-shot network traffic classification framework based on large language models (LLMs). By integrating meta-learning with LLMs, it reduces reliance on labeled data, eliminates task-specific training, and improves performance. Specifically, we first apply an efficient feature extraction method to extract features from traffic flows. We then design meta-tasks that combine task descriptions with textualized features to produce natural language meta-task formulations. Building on these meta-tasks, the LLM performs reasoning to carry out traffic classification. Finally, to mitigate hallucination in the LLM outputs, we exploit the temporal characteristics of network traffic and aggregate predictions over samples within a defined time window. Extensive experiments on three widely-used encrypted traffic datasets demonstrate that our proposed framework outperforms the state-of-the-art methods, achieving an average absolute improvement in F1 score of 9.75, 9.82, and 12.06 percentage points on the three datasets, respectively.
- 23 June 2026
- Published by Springer Nature
- p. 157-171
Modeling Semantic Ambiguity: A Knowledge-Driven Framework for Security Attack Technique Extraction
- 23 June 2026
- Published by Springer Nature
- p. 157-171
Modeling Semantic Ambiguity: A Knowledge-Driven Framework for Security Attack Technique Extraction
- Open Access
IID-DAKD: An Incremental Intrusion Detection Method for Encrypted Traffic Based on Dual Augmentation and Fusion Knowledge Distillation
To address the pronounced degradation in detection accuracy of encrypted traffic intrusion models after incremental updates, which is primarily caused by catastrophic forgetting and task-level overfitting during incremental learning, this paper proposes a novel incremental intrusion detection method for encrypted traffic based on dual augmentation and fusion knowledge distillation, termed IID-DAKD. First, both known and previously unseen attacks identified during detection are leveraged to update a representative sample set. An encrypted traffic representative sample augmentation strategy based on Gaussian noise is then devised to reduce storage requirements and classifier bias, thereby effectively mitigating catastrophic forgetting. Second, a self-supervised learning framework driven by encrypted traffic class augmentation is constructed to alleviate representation bias and suppress task-level overfitting. Finally, three complementary knowledge distillation strategies are jointly employed to extract and transfer attack classification knowledge from the old model to the updated model, further improving detection accuracy and robustness while enhancing training efficiency. Extensive experimental results demonstrate that the proposed IID-DAKD approach alleviates catastrophic forgetting and task-level overfitting while maintaining symmetrical knowledge transfer during incremental learning, enabling efficient model updates and high detection accuracy for encrypted traffic intrusion detection.
Open AccessIID-DAKD: An Incremental Intrusion Detection Method for Encrypted Traffic Based on Dual Augmentation and Fusion Knowledge Distillation
To address the pronounced degradation in detection accuracy of encrypted traffic intrusion models after incremental updates, which is primarily caused by catastrophic forgetting and task-level overfitting during incremental learning, this paper proposes a novel incremental intrusion detection method for encrypted traffic based on dual augmentation and fusion knowledge distillation, termed IID-DAKD. First, both known and previously unseen attacks identified during detection are leveraged to update a representative sample set. An encrypted traffic representative sample augmentation strategy based on Gaussian noise is then devised to reduce storage requirements and classifier bias, thereby effectively mitigating catastrophic forgetting. Second, a self-supervised learning framework driven by encrypted traffic class augmentation is constructed to alleviate representation bias and suppress task-level overfitting. Finally, three complementary knowledge distillation strategies are jointly employed to extract and transfer attack classification knowledge from the old model to the updated model, further improving detection accuracy and robustness while enhancing training efficiency. Extensive experimental results demonstrate that the proposed IID-DAKD approach alleviates catastrophic forgetting and task-level overfitting while maintaining symmetrical knowledge transfer during incremental learning, enabling efficient model updates and high detection accuracy for encrypted traffic intrusion detection.
- 30 November 2024
- Published by Springer Nature
- p. 124-140
UAD-DPL: An Unknown Encrypted Attack Detection Method Based on Deep Prototype Learning
- 30 November 2024
- Published by Springer Nature
- p. 124-140
UAD-DPL: An Unknown Encrypted Attack Detection Method Based on Deep Prototype Learning
- Open Access
FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification under Environment Shifts
Encrypted traffic classification plays a critical role in network security and management. Currently, mining deep patterns from side-channel contents and plaintext fields through neural networks is a major solution. However, existing methods have two major limitations: (1) They fail to recognize the critical link between transport layer mechanisms and applications, missing the opportunity to learn internal structure features for accurate traffic classification. (2) They assume network traffic in an unrealistically stable and singular environment, making it difficult to effectively classify real-world traffic under environment shifts. In this paper, we propose FG-SAT, the first end-to-end method for encrypted traffic analysis under environment shifts. We propose a key abstraction, the Flow Graph, to represent flow internal relationship structures and rich node attributes, which enables robust and generalized representation. Additionally, to address the problem of inconsistent data distribution under environment shifts, we introduce a novel feature selection algorithm based on Jensen-Shannon divergence (JSD) to select robust node attributes. Finally, we design a classifier, GraphSAT, which integrates GraphSAGE and GAT to deeply learn Flow Graph features, enabling accurate encrypted traffic identification. FG-SAT exhibits both efficient and robust classification performance under environment shifts and outperforms state-of-the-art methods in encrypted attack detection and application classification.
Open AccessFG-SAT: Efficient Flow Graph for Encrypted Traffic Classification under Environment Shifts
Encrypted traffic classification plays a critical role in network security and management. Currently, mining deep patterns from side-channel contents and plaintext fields through neural networks is a major solution. However, existing methods have two major limitations: (1) They fail to recognize the critical link between transport layer mechanisms and applications, missing the opportunity to learn internal structure features for accurate traffic classification. (2) They assume network traffic in an unrealistically stable and singular environment, making it difficult to effectively classify real-world traffic under environment shifts. In this paper, we propose FG-SAT, the first end-to-end method for encrypted traffic analysis under environment shifts. We propose a key abstraction, the Flow Graph, to represent flow internal relationship structures and rich node attributes, which enables robust and generalized representation. Additionally, to address the problem of inconsistent data distribution under environment shifts, we introduce a novel feature selection algorithm based on Jensen-Shannon divergence (JSD) to select robust node attributes. Finally, we design a classifier, GraphSAT, which integrates GraphSAGE and GAT to deeply learn Flow Graph features, enabling accurate encrypted traffic identification. FG-SAT exhibits both efficient and robust classification performance under environment shifts and outperforms state-of-the-art methods in encrypted attack detection and application classification.
- Open Access
- 21 July 2023
- Published by Springer Nature in Research Square
UAD-DPN: An Unknown Attack Detection Method for Encrypted Traffic Based on Deep Prototype Network
Intrusion detection systems (IDS) are well-known means of quickly detecting attacks, which can effectively detect known attacks available during training. However, when the system operates in a real open network environment, the attacks which it experiences may differ from those learned during training, which we call unknown attacks. Unknown attacks are significant threats, and their effects are the same as zero days. The main challenge of IDS is to detect unknown attacks and distinguish them from benign traffic and existing known attacks. There-fore, it is very importance to quantify to what extent an IDS can detect unknown attacks. But most existing deep learning methods for unknown attack detection cannot clearly recognize the deep features of unknown attack classes, which are inherently inaccurate. To solve these problems, an innovative unknown attack detection approach based on deep prototype network (UAD-DPN) is proposed to enhance the accuracy and efficiency of encrypted unknown attack detection. First, we employ an encrypted traffic spatiotemporal fusion feature extraction network to improve the feature representation ability. Then, we propose an innovative prototype-based encrypted traffic feature space learning model, which uses discriminative loss and open loss training models to improve the performance of encrypted unknown attacks detection. Finally, an unknown attack identification method based on the nearest prototype rule and a three-stage training approach for UAD-DPN model are designed to conveniently and effectively identify known attacks and reject unknown attacks. The experimental results demonstrated that the proposed UAD-DPN is very effective to detect both known and unknown attacks for encrypted traffic with higher accuracy and efficiency. Meanwhile, UAD-DPN have good application prospects in network intrusion detection system under the complex open network environment.
- 21 July 2023
- Published by Springer Nature in Research Square
Open AccessUAD-DPN: An Unknown Attack Detection Method for Encrypted Traffic Based on Deep Prototype Network
Intrusion detection systems (IDS) are well-known means of quickly detecting attacks, which can effectively detect known attacks available during training. However, when the system operates in a real open network environment, the attacks which it experiences may differ from those learned during training, which we call unknown attacks. Unknown attacks are significant threats, and their effects are the same as zero days. The main challenge of IDS is to detect unknown attacks and distinguish them from benign traffic and existing known attacks. There-fore, it is very importance to quantify to what extent an IDS can detect unknown attacks. But most existing deep learning methods for unknown attack detection cannot clearly recognize the deep features of unknown attack classes, which are inherently inaccurate. To solve these problems, an innovative unknown attack detection approach based on deep prototype network (UAD-DPN) is proposed to enhance the accuracy and efficiency of encrypted unknown attack detection. First, we employ an encrypted traffic spatiotemporal fusion feature extraction network to improve the feature representation ability. Then, we propose an innovative prototype-based encrypted traffic feature space learning model, which uses discriminative loss and open loss training models to improve the performance of encrypted unknown attacks detection. Finally, an unknown attack identification method based on the nearest prototype rule and a three-stage training approach for UAD-DPN model are designed to conveniently and effectively identify known attacks and reject unknown attacks. The experimental results demonstrated that the proposed UAD-DPN is very effective to detect both known and unknown attacks for encrypted traffic with higher accuracy and efficiency. Meanwhile, UAD-DPN have good application prospects in network intrusion detection system under the complex open network environment.
- 29 June 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (9) , 7489-7518
THS-IDPC: A three-stage hierarchical sampling method based on improved density peaks clustering algorithm for encrypted malicious traffic detection
- 29 June 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 76 (9) , 7489-7518
THS-IDPC: A three-stage hierarchical sampling method based on improved density peaks clustering algorithm for encrypted malicious traffic detection