Xiaoting Lyu

Xiaoting Lyu

Auto-generated profile, based on publicly available information

Xiaoting Lyu

Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 August 2024 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XLXiaoting Lyu
Xiaoting Lyu
YHYufei Han
Yufei Han
WWWei Wang
Wei Wang
JLJingkai Liu
Jingkai Liu
BWBin Wang
Bin Wang
XZXiangliang Zhang
Xiangliang Zhang
Considerable efforts have been devoted to addressing distributed backdoor attacks in federated learning (FL) systems. While significant progress has been made in enhancing the security of FL systems, our study reveals that there remains a false sense of security surrounding FL. We demonstrate that colluding malicious participants can effectively execute backdoor attacks during the FL training process, exhibiting high sparsity and stealthiness, which means they can evade common defense methods with only a few attack iterations. Our research highlights this vulnerability by proposing a Co llusive B ackdoor A ttack named CoBA . CoBA is designed to enhance the sparsity and stealthiness of backdoor attacks by offering trigger tuning to facilitate learning of backdoor training data, controlling the bias of malicious local model updates, and applying the projected gradient descent technique. By conducting extensive empirical studies on 5 benchmark datasets, we make the following observations: 1) CoBA successfully circumvents 15 state-of-the-art defense methods for robust FL; 2) Compared to existing backdoor attacks, CoBA consistently achieves superior attack performance; and 3) CoBA can achieve persistent poisoning effects through significantly sparse attack iterations. These findings raise substantial concerns regarding the integrity of FL and underscore the urgent need for heightened vigilance in defending against such attacks.

24 August 2024
Verified
Conference Paper
Open access
XLXiaoting Lyu
Xiaoting Lyu
YHYufei Han
Yufei Han
WWWei Wang
Wei Wang
HQHangwei Qian
Hangwei Qian
ITIvor Tsang
Ivor Tsang
XZXiangliang Zhang
Xiangliang Zhang
Graph Prompt Learning (GPL) bridges significant disparities between pretraining and downstream applications to alleviate the knowledge transfer bottleneck in real-world graph learning. While GPL offers superior effectiveness in graph knowledge transfer and computational efficiency, the security risks posed by backdoor poisoning effects embedded in pretrained models remain largely unexplored. Our study provides a comprehensive analysis of GPL's vulnerability to backdoor attacks. We introduce CrossBA, the first cross-context backdoor attack against GPL, which manipulates only the pretraining phase without requiring knowledge of downstream applications. Our investigation reveals both theoretically and empirically that tuning trigger graphs, combined with prompt transformations, can seamlessly transfer the backdoor threat from pretrained encoders to downstream applications.Through extensive experiments involving 3 representative GPL methods across 5 distinct cross-context scenarios and 5 benchmark datasets of node and graph classification tasks, we demonstrate that CrossBA consistently achieves high attack success rates while preserving the functionality of downstream applications over clean input. We also explore potential countermeasures against CrossBA and conclude that current defenses are insufficient to mitigate CrossBA. Our study highlights the persistent backdoor threats to GPL systems, raising trustworthiness concerns in the practices of GPL techniques.

2 December 2024
Verified
Conference Paper
Open access
YHYurong Hao
Yurong Hao
XCXihui Chen
Xihui Chen
XLXiaoting Lyu
Xiaoting Lyu
Jiqiang LiuJiqiang Liu
Jiqiang Liu
YZYongsheng Zhu
Yongsheng Zhu
WWWei Wang
Wei Wang
Federated recommendation (FR) is a decentralised approach to training personalised recommender systems, protecting users' privacy by avoiding data collection. Despite its privacy advantages, FR remains vulnerable to poisoning attacks. We focus on untargeted poisoning attacks against FR which degrade the overall performance of recommender services, leading to a detrimental impact on user experience and service quality. In this paper, we propose a general framework to formalise untargeted attacks and identify the vital role played by the interplay between items and user profiles in determining FR's performance. We present an untargeted attack FRecAttack2 which exploits this interplay. Specifically, we develop various methods for sampling user profiles, which approximate user distributions with and without collusion among malicious users. Then we leverage a new measurement to identify items that can disrupt the original interplay with user profiles, based on the change velocity of items' recommendation scores during optimisation. Extensive experiments demonstrate the superiority of our attack, outperforming existing methods by up to 27.56%, and its stealthiness in evading mainstream defences. To counteract untargeted attacks, we present a defence GuardCQ to detect malicious users by quantifying their contribution to boost the right interplay between items and user profiles. Empirical results show that GuardCQ effectively mitigates the attack's impact on FR and enhances the robustness of FR against poisoning attacks.

1 June 2024 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
JLJingkai Liu
Jingkai Liu
XLXiaoting Lyu
Xiaoting Lyu
Li DuanLi Duan
Li Duan
YHYongzhong He
Yongzhong He
Jiqiang LiuJiqiang Liu
Jiqiang Liu
WWWei Wang
Wei Wang
Federated learning (FL), which holds promise for use in edge intelligence applications for smart cities, enables smart devices collaborate in training a global model by exchanging local model updates instead of sharing local training data. However, the global model can be corrupted by malicious clients conducting poisoning attacks, resulting in the failure of converging the global model, incorrect predictions on the test set, or the backdoor embedded. Although some aggregation algorithms can enhance the robustness of FL against malicious clients, our work demonstrates that existing stealthy poisoning attacks can still bypass these defense methods. In this work, we propose a robust aggregation mechanism, called Parts and All ( PnA ), to protect the global model of FL by filtering out malicious local model updates throughout the detection of poisoning attacks at layers of local model updates. We conduct comprehensive experiments on three representative datasets. The experimental results demonstrate that our proposed PnA is more effective than existing robust aggregation algorithms against state-of-the-art poisoning attacks. Besides, PnA has a stable performance against poisoning attacks with different poisoning settings.

10 June 2026 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XLXiaoting Lyu
Xiaoting Lyu
YHYufei Han
Yufei Han
HQHangwei Qian
Hangwei Qian
ITIvor Tsang
Ivor Tsang
WWWei Wang
Wei Wang
Graph Prompt Learning (GPL) effectively bridges the gap between graph pre-training and downstream tasks, addressing the bottleneck in knowledge transfer. However, its susceptibility to backdoor attacks during pre-training remains largely unexplored. This work systematically investigates the backdoor risks in GPL and introduces TrojanGPL-a cross-context backdoor attack that embeds triggers solely through manipulations of the pre-trained encoder, independent of downstream knowledge. Our analysis reveals that jointly optimizing trigger graphs with the prompt mechanism not only narrows the gap between upstream and downstream main tasks but also aligns main and backdoor learning objectives, facilitating seamless backdoor transfer from pre-trained models to diverse downstream applications. To counter this threat, we propose ES-Detector, a defense mechanism that identifies backdoored graph samples by detecting discriminative embedding shifts upon the removal of important nodes. Specifically, when clean and backdoored graphs are predicted as the same class, clean graphs exhibit stable embedding changes, whereas backdoored graphs show significant deviations from clean ones. Extensive experiments on 5 benchmark datasets and 3 GPL frameworks demonstrate that TrojanGPL achieves an attack success rate exceeding 90% in different cross-context scenarios while minimally impacting the performance of the main task. Meanwhile, ES-Detector reduces the attack success rate by at least 60% across all the test settings, validating its practical robustness without prior knowledge of attack patterns.