Yue Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yue Wu has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Futai Zou
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
6 shared publications - Jiaping Gui
Shanghai Jiao Tong University, Shanghai, China
5 shared publications - Ping Yi
Shanghai Jiao Tong University, Shanghai, China
4 shared publications - Haiyang Yu
School of Computer Science, Shanghai Jiao Tong University, China
3 shared publications - Yue Bi
LTCI Telecom Paris IP Paris 91120 Palaiseau France
3 shared publications Fanchao Meng
Shanghai Jiao Tong University
2 shared publications
Latest Publications
- Open Access
- 15 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
FiCoVuL: A Framework for Fine-grained and Cross-function Code Vulnerability Detection
Detecting vulnerabilities in software development is crucial yet challenging. Deep learning-based approaches have shown promise in automatically learning features for vulnerable function detection. In practice, human analysts need to correlate the behavioral logic of multiple functions to confirm the occurrence of vulnerabilities. However, existing works fail to consider the contextual information across functions. Furthermore, human analysts expect models to provide finer-grained explanations to assist in the fixing process. In this paper, we present FiCoVuL, a framework for analyzing interconnected functions and providing fine-grained guidance for vulnerability fixing. FiCoVuL utilizes Function Fusion to extract function definitions and their call relationships from a project, and synthesize multiple functions into one for joint analysis. It models code as a multi-relational graph, capturing rich syntactic and semantic relationships between code statements. A multi-relational graph attention network is leveraged to perform message passing between nodes and edge relationships, generating graph-level and node-level representations. These representations are utilized for vulnerability function prediction and code line ranking, assisting in vulnerability fixing. We evaluate FiCoVuL on a public vulnerability dataset and a self-constructed cross-function one, and compare it with five existing detection models. Experimental results show that FiCoVuL significantly outperforms other methods in both vulnerability detection and localization.
- 15 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessFiCoVuL: A Framework for Fine-grained and Cross-function Code Vulnerability Detection
Detecting vulnerabilities in software development is crucial yet challenging. Deep learning-based approaches have shown promise in automatically learning features for vulnerable function detection. In practice, human analysts need to correlate the behavioral logic of multiple functions to confirm the occurrence of vulnerabilities. However, existing works fail to consider the contextual information across functions. Furthermore, human analysts expect models to provide finer-grained explanations to assist in the fixing process. In this paper, we present FiCoVuL, a framework for analyzing interconnected functions and providing fine-grained guidance for vulnerability fixing. FiCoVuL utilizes Function Fusion to extract function definitions and their call relationships from a project, and synthesize multiple functions into one for joint analysis. It models code as a multi-relational graph, capturing rich syntactic and semantic relationships between code statements. A multi-relational graph attention network is leveraged to perform message passing between nodes and edge relationships, generating graph-level and node-level representations. These representations are utilized for vulnerability function prediction and code line ranking, assisting in vulnerability fixing. We evaluate FiCoVuL on a public vulnerability dataset and a self-constructed cross-function one, and compare it with five existing detection models. Experimental results show that FiCoVuL significantly outperforms other methods in both vulnerability detection and localization.
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
SFBD: Backdoor Detection via Sequential Fingerprinting of Neural Networks for Securing the IoT Model Supply Chain
The rapid deployment of Deep Learning (DL) in the Internet of Things (IoT) increasingly relies on outsourcing model training to third parties or cloud servers due to the resource constraints of edge devices. In practical IoT scenarios, edge devices and gateways typically do not have access to original training data due to privacy regulations, fragmented data ownership, and regulatory constraints. However, these devices frequently receive third-party models or model updates through Firmware Over-The-Air (FOTA) mechanisms. This supply chain introduces severe security risks, especially backdoor attacks, where malicious triggers are embedded into models before deployment. As a result, IoT stakeholders must conduct network admission and pre-deployment auditing based solely on model weights, since clean datasets and trigger samples are not available for conventional analysis. Existing defense mechanisms that require input data or activation analysis are therefore impractical in IoT environments. To bridge this gap, we introduce a new paradigm for backdoor detection that inspects only the intrinsic properties of model weights. We propose Sequential Fingerprinting for Backdoor Detection (SFBD), a framework that treats a neural network as a structural sequence and constructs sequential fingerprints from model weights, enabling robust, data-free auditing before model deployment. By modeling cross-layer correlations, SFBD effectively identifies anomalies indicative of backdoors. In addition, SFBD is equipped with a few-shot learning mechanism, allowing it to rapidly adapt to novel OTA scenarios using only a small number of unlabeled candidate models. This makes SFBD an essential gatekeeper for secure IoT model updates. Comprehensive experiments across diverse backdoor attacks, datasets, model architectures, and a representative non-vision audio scenario show that SFBD achieves state-of-the-art performance in inference-data-free detection and strong cross-scenario generalization. Code is available at https://github.com/HaiyangYu-Lab/SFBD.
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
SFBD: Backdoor Detection via Sequential Fingerprinting of Neural Networks for Securing the IoT Model Supply Chain
The rapid deployment of Deep Learning (DL) in the Internet of Things (IoT) increasingly relies on outsourcing model training to third parties or cloud servers due to the resource constraints of edge devices. In practical IoT scenarios, edge devices and gateways typically do not have access to original training data due to privacy regulations, fragmented data ownership, and regulatory constraints. However, these devices frequently receive third-party models or model updates through Firmware Over-The-Air (FOTA) mechanisms. This supply chain introduces severe security risks, especially backdoor attacks, where malicious triggers are embedded into models before deployment. As a result, IoT stakeholders must conduct network admission and pre-deployment auditing based solely on model weights, since clean datasets and trigger samples are not available for conventional analysis. Existing defense mechanisms that require input data or activation analysis are therefore impractical in IoT environments. To bridge this gap, we introduce a new paradigm for backdoor detection that inspects only the intrinsic properties of model weights. We propose Sequential Fingerprinting for Backdoor Detection (SFBD), a framework that treats a neural network as a structural sequence and constructs sequential fingerprints from model weights, enabling robust, data-free auditing before model deployment. By modeling cross-layer correlations, SFBD effectively identifies anomalies indicative of backdoors. In addition, SFBD is equipped with a few-shot learning mechanism, allowing it to rapidly adapt to novel OTA scenarios using only a small number of unlabeled candidate models. This makes SFBD an essential gatekeeper for secure IoT model updates. Comprehensive experiments across diverse backdoor attacks, datasets, model architectures, and a representative non-vision audio scenario show that SFBD achieves state-of-the-art performance in inference-data-free detection and strong cross-scenario generalization. Code is available at https://github.com/HaiyangYu-Lab/SFBD.
- Open Access
RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models
Modern Network Intrusion Detection Systems generate vast volumes of low-level alerts, yet these outputs remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing solutions for automating this mapping-rule-based systems and machine learning classifiers-suffer from critical limitations: rule-based approaches fail to adapt to novel attack variations, while machine learning methods lack contextual awareness and treat tactic-technique mapping as a syntactic matching problem rather than a reasoning task. Although Large Language Models have shown promise in cybersecurity tasks, preliminary experiments reveal that existing LLM-based methods frequently hallucinate technique names or produce decontextualized mappings due to their single-step classification approach. To address these challenges, we introduce RHINO, a novel framework that decomposes LLM-based attack analysis into three interpretable phases mirroring human reasoning: (1) behavioral abstraction, where raw logs are translated into contextualized narratives; (2) multi-role collaborative inference, generating candidate techniques by evaluating behavioral evidence against MITRE ATT&CK knowledge; and (3) validation, cross-referencing predictions with official MITRE definitions to rectify hallucinations. RHINO bridges the semantic gap between low-level observations and adversarial intent while improving output reliability through structured reasoning. We evaluate RHINO on three benchmarks across four backbone models. RHINO achieved high accuracy, with model performance ranging from 86.38% to 88.45%, resulting in relative gains from 24.25% to 76.50% across different models. Our results demonstrate that RHINO significantly enhances the interpretability and scalability of threat analysis, offering a blueprint for deploying LLMs in operational security settings.
Open AccessRHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models
Modern Network Intrusion Detection Systems generate vast volumes of low-level alerts, yet these outputs remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing solutions for automating this mapping-rule-based systems and machine learning classifiers-suffer from critical limitations: rule-based approaches fail to adapt to novel attack variations, while machine learning methods lack contextual awareness and treat tactic-technique mapping as a syntactic matching problem rather than a reasoning task. Although Large Language Models have shown promise in cybersecurity tasks, preliminary experiments reveal that existing LLM-based methods frequently hallucinate technique names or produce decontextualized mappings due to their single-step classification approach. To address these challenges, we introduce RHINO, a novel framework that decomposes LLM-based attack analysis into three interpretable phases mirroring human reasoning: (1) behavioral abstraction, where raw logs are translated into contextualized narratives; (2) multi-role collaborative inference, generating candidate techniques by evaluating behavioral evidence against MITRE ATT&CK knowledge; and (3) validation, cross-referencing predictions with official MITRE definitions to rectify hallucinations. RHINO bridges the semantic gap between low-level observations and adversarial intent while improving output reliability through structured reasoning. We evaluate RHINO on three benchmarks across four backbone models. RHINO achieved high accuracy, with model performance ranging from 86.38% to 88.45%, resulting in relative gains from 24.25% to 76.50% across different models. Our results demonstrate that RHINO significantly enhances the interpretability and scalability of threat analysis, offering a blueprint for deploying LLMs in operational security settings.
- Open Access
Interference Alignment for Multi-cluster Over-the-Air Computation
One of the main challenges facing Internet of Things (IoT) networks is managing interference caused by the large number of devices communicating simultaneously, particularly in multi-cluster networks where multiple devices simultaneously transmit to their respective receiver. Over-the-Air Computation (AirComp) has emerged as a promising solution for efficient real-time data aggregation, yet its performance suffers in dense, interference-limited environments. To address this, we propose a novel Interference Alignment (IA) scheme tailored for up-link AirComp systems. Unlike previous approaches, the proposed method scales to an arbitrary number $\sf K$ of clusters and enables each cluster to exploit half of the available channels, instead of only $\tfrac{1}{\sf K}$ as in time-sharing. In addition, we develop schemes tailored to scenarios where users are shared between adjacent clusters.Open AccessInterference Alignment for Multi-cluster Over-the-Air Computation
One of the main challenges facing Internet of Things (IoT) networks is managing interference caused by the large number of devices communicating simultaneously, particularly in multi-cluster networks where multiple devices simultaneously transmit to their respective receiver. Over-the-Air Computation (AirComp) has emerged as a promising solution for efficient real-time data aggregation, yet its performance suffers in dense, interference-limited environments. To address this, we propose a novel Interference Alignment (IA) scheme tailored for up-link AirComp systems. Unlike previous approaches, the proposed method scales to an arbitrary number $\sf K$ of clusters and enables each cluster to exploit half of the available channels, instead of only $\tfrac{1}{\sf K}$ as in time-sharing. In addition, we develop schemes tailored to scenarios where users are shared between adjacent clusters. - Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2791-2802
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2791-2802
Open AccessBackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5356-5371
Dictionary Learning-Enabled Privacy Preserving Semantic Communication System
For deep learning-enabled semantic communication, existing privacy protection methods only take into account the presence of eavesdropper while ignoring malicious receiver aiming to detect confidential information. Only information-theoretical security can transmitter defend against malicious receiver. However, private information are always entangled with pragmatic information in feature space, which leads global perturbation to degrade communication performance. To handle these difficulties, in this paper a privacy preserving semantic communication system is proposed. Different from traditional paradigm, a novel privacy preserving semantic encoder is designed to realize targeted privacy protection while remaining useful information unaffected. Within proposed privacy preserving semantic encoder, feature decoupling module aims to disentangle semantic information by learning two sets of basis vectors which can express private and pragmatic information of data, respectively. Accordingly differential privacy mechanism is employed to provide information-theoretical security. Experimental results demonstrate that proposed method not only achieves better communication performance in both data recovery and pragmatic task, but also more effectively degrades the accuracy of malicious receiver to infer sensitive information than global perturbation does.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5356-5371
Dictionary Learning-Enabled Privacy Preserving Semantic Communication System
For deep learning-enabled semantic communication, existing privacy protection methods only take into account the presence of eavesdropper while ignoring malicious receiver aiming to detect confidential information. Only information-theoretical security can transmitter defend against malicious receiver. However, private information are always entangled with pragmatic information in feature space, which leads global perturbation to degrade communication performance. To handle these difficulties, in this paper a privacy preserving semantic communication system is proposed. Different from traditional paradigm, a novel privacy preserving semantic encoder is designed to realize targeted privacy protection while remaining useful information unaffected. Within proposed privacy preserving semantic encoder, feature decoupling module aims to disentangle semantic information by learning two sets of basis vectors which can express private and pragmatic information of data, respectively. Accordingly differential privacy mechanism is employed to provide information-theoretical security. Experimental results demonstrate that proposed method not only achieves better communication performance in both data recovery and pragmatic task, but also more effectively degrades the accuracy of malicious receiver to infer sensitive information than global perturbation does.
- 22 May 2025
- Published by Elsevier in Computers & Security
- Vol. 156
DISTR: Detecting multi-stage IoT botnets through contextual traffic and causal analytics
- 22 May 2025
- Published by Elsevier in Computers & Security
- Vol. 156
DISTR: Detecting multi-stage IoT botnets through contextual traffic and causal analytics
- 14 July 2024
- Published by Elsevier in Computers & Security
- Vol. 144
Few-VulD: A Few-shot learning framework for software vulnerability detection
- 14 July 2024
- Published by Elsevier in Computers & Security
- Vol. 144
Few-VulD: A Few-shot learning framework for software vulnerability detection
- Open Access
DoF Analysis for (M, N)-Channels through a Number-Filling Puzzle
We consider a $\sf K$ user interference network with general connectivity, described by a matrix $\mat{N}$, and general message flows, described by a matrix $\mat{M}$. Previous studies have demonstrated that the standard interference scheme (IA) might not be optimal for networks with sparse connectivity. In this paper, we formalize a general IA coding scheme and an intuitive number-filling puzzle for given $\mat{M}$ and $\mat{N}$ in a way that the score of the solution to the puzzle determines the optimum sum degrees that can be achieved by the IA scheme. A solution to the puzzle is proposed for a general class of symmetric channels, and it is shown that this solution leads to significantly higher $\SDoF$ than the standard IA scheme.Open AccessDoF Analysis for (M, N)-Channels through a Number-Filling Puzzle
We consider a $\sf K$ user interference network with general connectivity, described by a matrix $\mat{N}$, and general message flows, described by a matrix $\mat{M}$. Previous studies have demonstrated that the standard interference scheme (IA) might not be optimal for networks with sparse connectivity. In this paper, we formalize a general IA coding scheme and an intuitive number-filling puzzle for given $\mat{M}$ and $\mat{N}$ in a way that the score of the solution to the puzzle determines the optimum sum degrees that can be achieved by the IA scheme. A solution to the puzzle is proposed for a general class of symmetric channels, and it is shown that this solution leads to significantly higher $\SDoF$ than the standard IA scheme.