Xun Lin

Xun Lin

Auto-generated profile, based on publicly available information

Xun Lin

Chinese University of Hong Kong

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
11 September 2023 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
YLYizhong Liu
Yizhong Liu
XXXinxin Xing
Xinxin Xing
ZTZiheng Tong
Ziheng Tong
XLXun Lin
Xun Lin
Jing ChenJing Chen
Jing Chen
Willy SusiloWilly Susilo
Willy Susilo
The cloud-edge-end architecture is suitable for many essential scenarios, such as 5 G, the Internet of Things (IoT), and mobile edge computing. Under this architecture, cross-domain and cross-layer data sharing is commonly in need. Considering cross-domain data sharing under the zero-trust model, where each entity does not trust the others, existing solutions have certain problems regarding security, fairness, scalability, and efficiency. Aiming at solving these issues, we conduct the following research. First, a new plaintext checkable encryption scheme is constructed, which can be used on lightweight IoT devices to verify the ciphertext validity sent by a data owner. Second, we propose a new multi-domain cloud-edge-end architecture based on sharding blockchains and design a cross-domain data sharing scheme under the partial trust model to achieve security, scalability, and high performance. Third, a cross-domain data sharing scheme under the zero trust model is further designed, which can ensure the fairness of both parties in data sharing. Fourth, we give a formal security definition and analysis of cross-domain data sharing. Fifth, we conduct a detailed theoretical analysis of the protocol and give an in-depth functional test and performance test, including the throughput and latency of data sharing policy registration and execution.

18 April 2024 in Information Fusion
Verified
Journal Article
Closed access
XQXiaolei Qu
Xiaolei Qu
JZJiale Zhou
Jiale Zhou
JJJue Jiang
Jue Jiang
WWWenhan Wang
Wenhan Wang
HWHaoran Wang
Haoran Wang
XLXun Lin
Xun Lin

26 May 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XLXun Lin
Xun Lin
ALAjian Liu
Ajian Liu
ZYZitong Yu
Zitong Yu
RCRizhao Cai
Rizhao Cai
SWShuai Wang
Shuai Wang
AKAlex Kot
Alex Kot
Face Anti-Spoofing (FAS) is essential for securing face recognition systems against presentation attacks. Recent advances in sensor technology and multimodal learning have enabled the development of multimodal FAS systems. However, existing methods often struggle to generalize to unseen attacks and diverse environments due to two key challenges: (1) Modality unreliability, where sensors such as depth and infrared suffer from severe domain shifts, impairing the reliability of cross-modal fusion; and (2) Modality imbalance, where over-reliance on a dominant modality weakens the model’s robustness against attacks that affect other modalities. To overcome these issues, we propose MMDG++, a multimodal domain-generalized FAS framework built upon the vision-language model CLIP. In MMDG++, we design the Uncertainty-Guided Cross-Adapter++ (U-Adapter++) to filter out unreliable regions within each modality, enabling more reliable multimodal interactions. Additionally, we introduce Rebalanced Modality Gradient Modulation (ReGrad) for adaptive gradient modulation to balance modality convergence. To further enhance generalization, propose Asymmetric Domain Prompts (ADPs) that leverage CLIP’s language priors to learn generalized decision boundaries across modalities. We also develop a novel multimodal FAS benchmark to evaluate generalizability under various deployment conditions. Extensive experiments across this benchmark show our method outperforms state-of-the-art FAS methods, demonstrating superior generalization capability.

20 August 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
RCRizhao Cai
Rizhao Cai
YCYawen Cui
Yawen Cui
ZYZitong Yu
Zitong Yu
XLXun Lin
Xun Lin
CCChangsheng Chen
Changsheng Chen
AKAlex Kot
Alex Kot
Face Anti-Spoofing (FAS) is constantly challenged by new attack types and mediums, and thus it is crucial for a FAS model to not only mitigate Catastrophic Forgetting (CF) of previously learned spoofing knowledge on the training data during continual learning but also enhance the model’s generalization ability to potential spoofing attacks. In this paper, we first highlight that current strategies for catastrophic forgetting are not well-suited to the imperceptible nature of spoofing information in FAS and lack the focus on improving generalization capability. Then, the instance-wise dynamic central difference convolutional adapter module with the weighted ensemble strategy for Vision Transformer (ViT) is proposed for efficiently fine-tuning with low-shot data by extracting generalized spoofing texture information. Furthermore, we find that catastrophic forgetting in FAS can be reflected through the inconsistent attention matrices of ViT between different continual sessions, as the attention matrices embody relationships of spoofing clues between different patch tokens. Hence, we introduce attention consistency regularization by learning and reusing attention matrices to alleviate catastrophic forgetting. Finally, we devise new protocols and conduct extensive experiments to validate the superior performance of alleviating catastrophic forgetting and generalization on unseen domains.

19 March 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YYYi Yu
Yi Yu
SXSong Xia
Song Xia
XLXun Lin
Xun Lin
CKChenqi Kong
Chenqi Kong
WYWenhan Yang
Wenhan Yang
AKAlex C. Kot
Alex C. Kot
Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive unseen models in black-box scenarios. Despite the widespread exploration of defense methods, including those on transferability, they show limitations: inefficient deployment, ineffective defense, and degraded performance on clean images. In this work, we introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way.We propose a model that exhibits random guessing behavior when presented with clean data x as input, and generates accurate predictions when with triggered data x + τ . Importantly, the trigger τ remains constant for all data instances. We refer to these models as models with trigger activation. We are surprised to find that these models exhibit certain robustness against TAEs. Through the consideration of first-order gradients, we provide a theoretical analysis of this robustness. Moreover, through the joint optimization of the learnable trigger and the model, we achieve improved robustness to transferable attacks. Extensive experiments conducted across diverse datasets, evaluating a variety of attacking methods, underscore the effectiveness and superiority of our approach.

22 January 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YLYizhong Liu
Yizhong Liu
BZBoyu Zhao
Boyu Zhao
MZMingzhe Zhai
Mingzhe Zhai
XLXun Lin
Xun Lin
CYChenhao Ying
Chenhao Ying
RDRobert H. Deng
Robert H. Deng
Byzantine Fault Tolerance (BFT) protocols are a critical research area in distributed systems and blockchain consensus due to their capacity to deliver high throughput and low latency. Traditional BFT protocols typically rely on a single leader to propose transactions and aggregate votes, which often creates a bottleneck due to the leader’s limited communication and computational capacities. The introduction of multi-leader BFT has the potential to mitigate this issue by increasing system parallelism. However, existing approaches fail to address the challenge of electing multiple leaders and lack a comprehensive analysis of the relationship between the number of leaders, security constraints, and system throughput. In this paper, we study the performance and security of multi-leader BFT protocols. Initially, we introduce a secret multi-leader election method resistant to corruption attacks where selected leaders’ identities remain unknown to others until they proposes transactions. Then, we present specific multi-leader BFT constructions that support a pipelined processing methods, realizing high processing parallelism and optimized throughput. Besides, a cross-leader view-change mechanism is designed for multi-leader BFT to enable efficient replacement of malicious leaders. Furthermore, we analyze the impact of the number of leaders on security and demonstrate that our proposals meet the required security standards. Experimental results reveal that the system achieves a throughput of up to 101 ktx/sec with 128 nodes, highlighting the potential of multi-leader BFT to significantly enhance the performance of blockchain systems.