Jiawei Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiawei Ye has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Jie Wu
Fudan University, Shanghai, China
6 shared publications - Sicheng Liang
Fudan University, Shanghai, China
5 shared publications Jie Wu
College of Computer Science and Artificial Intelligence Fudan University
4 shared publications- Hongyi Li
College of Computer Science and Artificial Intelligence Fudan University
3 shared publications - Yu Liu
Fudan University
3 shared publications - Zhihui Lu
Fudan University
3 shared publications
Latest Publications
- 18 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
CoMAG: Collaborative GNN–LLM learning for multimodal attributed graphs
- 18 August 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 351
CoMAG: Collaborative GNN–LLM learning for multimodal attributed graphs
- Open Access
- 17 May 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (5) , 265
Graph-Aware Scheduling for Multi-Agent Workflows in Edge-Cloud Environments
Multi-agent workflows have emerged as an important execution pattern for intelligent applications, where specialized agents collaborate through dependent stages such as planning, retrieval, execution, and verification. When such workflows are deployed over edge-cloud infrastructures, scheduling becomes challenging because task dependencies, heterogeneous resource conditions, and topology-dependent communication overhead must be considered jointly. We study the problem of scheduling multi-agent workflows in edge-cloud environments and propose a graph-aware scheduling method that models workflow execution as a task graph and the underlying infrastructure as a resource graph. The method combines structure-aware task and resource representations, communication-sensitive assignment scoring, and online resource-state updates to improve task placement quality. Experiments across different workflow complexities, system scales, and dynamic operating conditions show that the proposed method achieves a favorable balance among latency, communication overhead, and execution cost, particularly in communication-sensitive and medium-to-large-scale settings. These results suggest that jointly modeling workflow structure and resource topology can improve scheduling quality for multi-agent workflow execution in heterogeneous edge-cloud environments.
- 17 May 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (5) , 265
Open AccessGraph-Aware Scheduling for Multi-Agent Workflows in Edge-Cloud Environments
Multi-agent workflows have emerged as an important execution pattern for intelligent applications, where specialized agents collaborate through dependent stages such as planning, retrieval, execution, and verification. When such workflows are deployed over edge-cloud infrastructures, scheduling becomes challenging because task dependencies, heterogeneous resource conditions, and topology-dependent communication overhead must be considered jointly. We study the problem of scheduling multi-agent workflows in edge-cloud environments and propose a graph-aware scheduling method that models workflow execution as a task graph and the underlying infrastructure as a resource graph. The method combines structure-aware task and resource representations, communication-sensitive assignment scoring, and online resource-state updates to improve task placement quality. Experiments across different workflow complexities, system scales, and dynamic operating conditions show that the proposed method achieves a favorable balance among latency, communication overhead, and execution cost, particularly in communication-sensitive and medium-to-large-scale settings. These results suggest that jointly modeling workflow structure and resource topology can improve scheduling quality for multi-agent workflow execution in heterogeneous edge-cloud environments.
- Open Access
StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak
Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prompts to bypass alignment. Existing efforts primarily rely on converting text-based attacks into speech or applying shallow signal-level perturbations, overlooking the impact of human speech's expressive variations on LAM alignment robustness. To address this gap, we propose StyleBreak, a novel style-aware audio jailbreak framework that systematically investigates how diverse human speech attributes affect LAM alignment robustness. Specifically, StyleBreak employs a two-stage style-aware transformation pipeline that perturbs both textual content and audio to control linguistic, paralinguistic, and extralinguistic attributes. Furthermore, we develop a query-adaptive policy network that automatically searches for adversarial styles to enhance the efficiency of LAM jailbreak exploration. Extensive evaluations demonstrate that LAMs exhibit critical vulnerabilities when exposed to diverse human speech attributes. Moreover, StyleBreak achieves substantial improvements in attack effectiveness and efficiency across multiple attack paradigms, highlighting the urgent need for more robust alignment in LAMs.
Open AccessStyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak
Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prompts to bypass alignment. Existing efforts primarily rely on converting text-based attacks into speech or applying shallow signal-level perturbations, overlooking the impact of human speech's expressive variations on LAM alignment robustness. To address this gap, we propose StyleBreak, a novel style-aware audio jailbreak framework that systematically investigates how diverse human speech attributes affect LAM alignment robustness. Specifically, StyleBreak employs a two-stage style-aware transformation pipeline that perturbs both textual content and audio to control linguistic, paralinguistic, and extralinguistic attributes. Furthermore, we develop a query-adaptive policy network that automatically searches for adversarial styles to enhance the efficiency of LAM jailbreak exploration. Extensive evaluations demonstrate that LAMs exhibit critical vulnerabilities when exposed to diverse human speech attributes. Moreover, StyleBreak achieves substantial improvements in attack effectiveness and efficiency across multiple attack paradigms, highlighting the urgent need for more robust alignment in LAMs.
- 4 October 2025
- Published by Springer Nature
- p. 176-192
HCT: A Hierarchical Contrastive Learning Framework for Transferable Graph Anomaly Detection
- 4 October 2025
- Published by Springer Nature
- p. 176-192
HCT: A Hierarchical Contrastive Learning Framework for Transferable Graph Anomaly Detection
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1707-1717
Feature Reconstruction for Anomaly Detection on Directed Multigraphs: A Preprocessing Framework for GNNs
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1707-1717
Open AccessFeature Reconstruction for Anomaly Detection on Directed Multigraphs: A Preprocessing Framework for GNNs
- Open Access
- 14 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 218
U-SCAD: An Unsupervised Method of System Call-Driven Anomaly Detection for Containerized Edge Clouds
Container technology is currently one of the mainstream technologies in the field of cloud computing, yet its adoption in resource-constrained, latency-sensitive edge environments introduces unique security challenges. While existing system call-based anomaly-detection methods partially address these issues, they suffer from high false positive rates and excessive computational overhead. To achieve security and observability in edge-native containerized environments and lower the cost of computing resources, we propose an unsupervised anomaly-detection method based on system calls. This method filters out unnecessary system call data through automatic rule generation and an unsupervised classification model. To increase the accuracy of anomaly detection and reduce the false positive rates, this method embeds system calls into sequences using the proposed Syscall2vec and processes the remain sequences in favor of the anomaly detection model’s analysis. We conduct experiments using our method with a background based on modern containerized cloud microservices. The results show that the detection part of our method improves the F1 score by 23.88% and 41.31%, respectively, as compared to HIDS and LSTM-VAE. Moreover, our method can effectively reduce the original processing data to 13%, which means that it significantly lowers the cost of computing resources.
- 14 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 218
Open AccessU-SCAD: An Unsupervised Method of System Call-Driven Anomaly Detection for Containerized Edge Clouds
Container technology is currently one of the mainstream technologies in the field of cloud computing, yet its adoption in resource-constrained, latency-sensitive edge environments introduces unique security challenges. While existing system call-based anomaly-detection methods partially address these issues, they suffer from high false positive rates and excessive computational overhead. To achieve security and observability in edge-native containerized environments and lower the cost of computing resources, we propose an unsupervised anomaly-detection method based on system calls. This method filters out unnecessary system call data through automatic rule generation and an unsupervised classification model. To increase the accuracy of anomaly detection and reduce the false positive rates, this method embeds system calls into sequences using the proposed Syscall2vec and processes the remain sequences in favor of the anomaly detection model’s analysis. We conduct experiments using our method with a background based on modern containerized cloud microservices. The results show that the detection part of our method improves the F1 score by 23.88% and 41.31%, respectively, as compared to HIDS and LSTM-VAE. Moreover, our method can effectively reduce the original processing data to 13%, which means that it significantly lowers the cost of computing resources.
- Open Access
- 5 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 208
A Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios
This paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competition, and environmental interference have led to significant packet loss rates, adversely impacting deep learning-based network traffic analysis tasks. To address this issue, TCReC leverages masked autoencoder techniques to reconstruct missing traffic features, ensuring reliable input for downstream tasks in edge computing scenarios. Experimental results demonstrate that TCReC maintains detection model accuracy within 10% of the original data, even under packet loss rates as high as 70%. For instance, on the ISCX-VPN-2016 dataset, TCReC achieves a Reconstruction Ability Index (RAI) of 94.02%, while on the CIC-IDS-2017 dataset, it achieves an RAI of 94.99% when combined with LSTM, significantly outperforming other methods such as Transformer, KNN, and RNN. Additionally, TCReC exhibits robustness across various packet loss scenarios, consistently delivering high-quality feature reconstruction for both attack traffic and common Internet application data. TCReC provides a robust solution for network traffic analysis in high-loss edge computing scenarios, offering practical value for real-world deployment.
- 5 May 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (5) , 208
Open AccessA Network Traffic Characteristics Reconstruction Method for Mitigating the Impact of Packet Loss in Edge Computing Scenarios
This paper presents TCReC, an innovative model designed for reconstructing network traffic characteristics in the presence of packet loss. With the rapid expansion of wireless networks driven by edge computing, IoT, and 5G technologies, challenges such as transmission instability, channel competition, and environmental interference have led to significant packet loss rates, adversely impacting deep learning-based network traffic analysis tasks. To address this issue, TCReC leverages masked autoencoder techniques to reconstruct missing traffic features, ensuring reliable input for downstream tasks in edge computing scenarios. Experimental results demonstrate that TCReC maintains detection model accuracy within 10% of the original data, even under packet loss rates as high as 70%. For instance, on the ISCX-VPN-2016 dataset, TCReC achieves a Reconstruction Ability Index (RAI) of 94.02%, while on the CIC-IDS-2017 dataset, it achieves an RAI of 94.99% when combined with LSTM, significantly outperforming other methods such as Transformer, KNN, and RNN. Additionally, TCReC exhibits robustness across various packet loss scenarios, consistently delivering high-quality feature reconstruction for both attack traffic and common Internet application data. TCReC provides a robust solution for network traffic analysis in high-loss edge computing scenarios, offering practical value for real-world deployment.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (26) , 27419-27427
JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLMs and further guides us in enhancing their security. Unfortunately, existing techniques mainly rely on handcrafted templates or generated-based optimization, posing challenges in scalability, efficiency and universality. To address these issues, we present JailPO, a novel black-box jailbreak framework to examine LLM alignment. For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts. Furthermore, we introduce a preference optimization-based attack method to enhance the jailbreak effectiveness, thereby improving efficiency. To analyze model vulnerabilities, we provide three flexible jailbreak patterns. Extensive experiments demonstrate that JailPO not only automates the attack process while maintaining effectiveness but also exhibits superior performance in efficiency, universality, and robustness against defenses compared to baselines. Additionally, our analysis of the three JailPO patterns reveals that attacks based on complex templates exhibit higher attack strength, whereas covert question transformations elicit riskier responses and are more likely to bypass defense mechanisms.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (26) , 27419-27427
Open AccessJailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLMs and further guides us in enhancing their security. Unfortunately, existing techniques mainly rely on handcrafted templates or generated-based optimization, posing challenges in scalability, efficiency and universality. To address these issues, we present JailPO, a novel black-box jailbreak framework to examine LLM alignment. For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts. Furthermore, we introduce a preference optimization-based attack method to enhance the jailbreak effectiveness, thereby improving efficiency. To analyze model vulnerabilities, we provide three flexible jailbreak patterns. Extensive experiments demonstrate that JailPO not only automates the attack process while maintaining effectiveness but also exhibits superior performance in efficiency, universality, and robustness against defenses compared to baselines. Additionally, our analysis of the three JailPO patterns reveals that attacks based on complex templates exhibit higher attack strength, whereas covert question transformations elicit riskier responses and are more likely to bypass defense mechanisms.
- 28 January 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 19 (10) , 1-15
Privacy dilemmas and opportunities in large language models: a brief review
- 28 January 2025
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 19 (10) , 1-15
Privacy dilemmas and opportunities in large language models: a brief review
- Open Access
JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLMs and further guides us in enhancing their security. Unfortunately, existing techniques mainly rely on handcrafted templates or generated-based optimization, posing challenges in scalability, efficiency and universality. To address these issues, we present JailPO, a novel black-box jailbreak framework to examine LLM alignment. For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts. Furthermore, we introduce a preference optimization-based attack method to enhance the jailbreak effectiveness, thereby improving efficiency. To analyze model vulnerabilities, we provide three flexible jailbreak patterns. Extensive experiments demonstrate that JailPO not only automates the attack process while maintaining effectiveness but also exhibits superior performance in efficiency, universality, and robustness against defenses compared to baselines. Additionally, our analysis of the three JailPO patterns reveals that attacks based on complex templates exhibit higher attack strength, whereas covert question transformations elicit riskier responses and are more likely to bypass defense mechanisms.
Open AccessJailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLMs and further guides us in enhancing their security. Unfortunately, existing techniques mainly rely on handcrafted templates or generated-based optimization, posing challenges in scalability, efficiency and universality. To address these issues, we present JailPO, a novel black-box jailbreak framework to examine LLM alignment. For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts. Furthermore, we introduce a preference optimization-based attack method to enhance the jailbreak effectiveness, thereby improving efficiency. To analyze model vulnerabilities, we provide three flexible jailbreak patterns. Extensive experiments demonstrate that JailPO not only automates the attack process while maintaining effectiveness but also exhibits superior performance in efficiency, universality, and robustness against defenses compared to baselines. Additionally, our analysis of the three JailPO patterns reveals that attacks based on complex templates exhibit higher attack strength, whereas covert question transformations elicit riskier responses and are more likely to bypass defense mechanisms.