Xinxin Fan
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
Research Subjects
Research Interests
Xinxin Fan has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Chi Lin
Dalian University of Technology
5 shared publications Quanliang Jing
Institute of Computing Technology Chinese Academy of Sciences
4 shared publicationsJingping Bi
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3 shared publications- Jingping Bi
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3 shared publications - Quanliang Jing
Institute of Computing Technology, Beijing, China, Beijing, Chile
2 shared publications Yunfeng Lu
School of Reliability and Systems, Beihang University, Beijing, China
2 shared publications
Latest Publications
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (2) , 1277-1290
GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service
Gradient leakage attacks pose a significant privacy threat in distributed learning-as-a-service APIs. Existing literature on gradient leakage defense relies on gradient perturbation for preventing privacy leakage. However, determining where and how much to perturb the gradient offers different capabilities for preventing gradient leakage. This paper presents GradCloak, a principled approach to guiding gradient perturbation with theoretical robustness bounds in federated learning as a service, aiming to find the minimum required noise for simultaneously achieving privacy protection, competitive accuracy, and preventing gradient leakage attacks. The paper is organized into three major components. First, we formulate the gradient leakage threats and their adverse effect. We categorize the attack into two broad types: leakage during local training and leakage before global aggregation. Second, we investigate different gradient perturbation approaches. We analyze and compare these gradient perturbation methods, which are performed at the federated server, with those performed at the participating client(s). Third, we introduce three robustness properties of robust perturbation against gradient leakage threats, formulated by the anonymization bound for training data robustness, the perturbation bound for gradient robustness, and the distribution robustness bound for perturbed gradients. We conduct extensive evaluations on eight benchmark datasets to demonstrate that specific settings of gradient perturbation exist that best balance privacy, accuracy, and leakage prevention. Code is available at https://github.com/git-disl/GradCloak.
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (2) , 1277-1290
GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service
Gradient leakage attacks pose a significant privacy threat in distributed learning-as-a-service APIs. Existing literature on gradient leakage defense relies on gradient perturbation for preventing privacy leakage. However, determining where and how much to perturb the gradient offers different capabilities for preventing gradient leakage. This paper presents GradCloak, a principled approach to guiding gradient perturbation with theoretical robustness bounds in federated learning as a service, aiming to find the minimum required noise for simultaneously achieving privacy protection, competitive accuracy, and preventing gradient leakage attacks. The paper is organized into three major components. First, we formulate the gradient leakage threats and their adverse effect. We categorize the attack into two broad types: leakage during local training and leakage before global aggregation. Second, we investigate different gradient perturbation approaches. We analyze and compare these gradient perturbation methods, which are performed at the federated server, with those performed at the participating client(s). Third, we introduce three robustness properties of robust perturbation against gradient leakage threats, formulated by the anonymization bound for training data robustness, the perturbation bound for gradient robustness, and the distribution robustness bound for perturbed gradients. We conduct extensive evaluations on eight benchmark datasets to demonstrate that specific settings of gradient perturbation exist that best balance privacy, accuracy, and leakage prevention. Code is available at https://github.com/git-disl/GradCloak.
- Open Access
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 389-393
SifterNet: Model-Agnostic Defense against Backdoor Attack in Vision Large Model
- 11 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 389-393
Open AccessSifterNet: Model-Agnostic Defense against Backdoor Attack in Vision Large Model
- Open Access
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be obtained through retrieving relational structure of entities from knowledge graph (KG). Regarding the inherent relation-dependency and reasoning pattern, multi-hop reasoning can be in general classified into two categories: i) parallel fact-verification multi-hop reasoning question, i.e., requiring simultaneous verifications of multiple independent sub-questions; and ii) chained multi-hop reasoning questions, i.e., demanding sequential multi-step inference with intermediate conclusions serving as essential premises for subsequent reasoning. Currently, the multi-hop reasoning approaches singly employ one of two techniques: LLM response-based fact verification and KG path-based chain construction. Nevertheless, the former excels at parallel fact-verification but underperforms on chained reasoning tasks, while the latter demonstrates proficiency in chained multi-hop reasoning but suffers from redundant path retrieval when handling parallel fact-verification reasoning. These limitations deteriorate the efficiency and accuracy for multi-hop QA tasks. To address this challenge, we propose a novel dual-track KG verification and reasoning framework DTKG, which is inspired by the Dual Process Theory in cognitive science. Specifically, DTKG comprises two main stages: the Classification Stage and the Branch Processing Stage.
Open AccessDTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be obtained through retrieving relational structure of entities from knowledge graph (KG). Regarding the inherent relation-dependency and reasoning pattern, multi-hop reasoning can be in general classified into two categories: i) parallel fact-verification multi-hop reasoning question, i.e., requiring simultaneous verifications of multiple independent sub-questions; and ii) chained multi-hop reasoning questions, i.e., demanding sequential multi-step inference with intermediate conclusions serving as essential premises for subsequent reasoning. Currently, the multi-hop reasoning approaches singly employ one of two techniques: LLM response-based fact verification and KG path-based chain construction. Nevertheless, the former excels at parallel fact-verification but underperforms on chained reasoning tasks, while the latter demonstrates proficiency in chained multi-hop reasoning but suffers from redundant path retrieval when handling parallel fact-verification reasoning. These limitations deteriorate the efficiency and accuracy for multi-hop QA tasks. To address this challenge, we propose a novel dual-track KG verification and reasoning framework DTKG, which is inspired by the Dual Process Theory in cognitive science. Specifically, DTKG comprises two main stages: the Classification Stage and the Branch Processing Stage.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (2) , 1870-1884
Secure Charging Scheduling in Wireless Rechargeable Sensor Networks
Wireless Rechargeable Sensor Networks (WRSNs) promise to address the limited energy resource issue for sensor nodes through wireless power transfer technology. However, WRSNs are vulnerable to various security threats, such as compromised node attack and malicious mobile charger (MC) attack, which can disrupt the charging process and degrade charging efficiency. In this work, we investigate the eneRgy conversion Efficiency maximization problem unDer chargIng attackS (REDIS). We propose a blockchain-based framework that employs a lightweight multi-layer storage approach tailored for resource-constrained sensor nodes and features consensus algorithms that validate charging transactions. Furthermore, we introduce a validation node selection strategy that integrates consensus execution with charging scheduling, reducing energy consumption, and improving energy efficiency. Extensive simulations and experiments validate the effectiveness of our framework, improving energy efficiency by 30% and as much as 5 times in networks without attacks and those under full attacks, respectively.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (2) , 1870-1884
Secure Charging Scheduling in Wireless Rechargeable Sensor Networks
Wireless Rechargeable Sensor Networks (WRSNs) promise to address the limited energy resource issue for sensor nodes through wireless power transfer technology. However, WRSNs are vulnerable to various security threats, such as compromised node attack and malicious mobile charger (MC) attack, which can disrupt the charging process and degrade charging efficiency. In this work, we investigate the eneRgy conversion Efficiency maximization problem unDer chargIng attackS (REDIS). We propose a blockchain-based framework that employs a lightweight multi-layer storage approach tailored for resource-constrained sensor nodes and features consensus algorithms that validate charging transactions. Furthermore, we introduce a validation node selection strategy that integrates consensus execution with charging scheduling, reducing energy consumption, and improving energy efficiency. Extensive simulations and experiments validate the effectiveness of our framework, improving energy efficiency by 30% and as much as 5 times in networks without attacks and those under full attacks, respectively.
- Open Access
SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach
Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purification approach resorting to the classic Ising model. To date, existing trigger detection/removal studies usually require to know the detailed knowledge of target model in advance, access to a large number of clean samples or even model-retraining authorization, which brings the huge inconvenience for practical applications, especially inaccessible to target model. An ideal countermeasure ought to eliminate the implanted trigger without regarding whatever the target models are. To this end, a lightweight and black-box defense approach SifterNet is proposed through leveraging the memorization-association functionality of Hopfield network, by which the triggers of input samples can be effectively purified in a proper manner. The main novelty of our proposed approach lies in the introduction of ideology of Ising model. Extensive experiments also validate the effectiveness of our approach in terms of proper trigger purification and high accuracy achievement, and compared to the state-of-the-art baselines under several commonly-used datasets, our SiferNet has a significant superior performance.
Open AccessSifterNet: A Generalized and Model-Agnostic Trigger Purification Approach
Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purification approach resorting to the classic Ising model. To date, existing trigger detection/removal studies usually require to know the detailed knowledge of target model in advance, access to a large number of clean samples or even model-retraining authorization, which brings the huge inconvenience for practical applications, especially inaccessible to target model. An ideal countermeasure ought to eliminate the implanted trigger without regarding whatever the target models are. To this end, a lightweight and black-box defense approach SifterNet is proposed through leveraging the memorization-association functionality of Hopfield network, by which the triggers of input samples can be effectively purified in a proper manner. The main novelty of our proposed approach lies in the introduction of ideology of Ising model. Extensive experiments also validate the effectiveness of our approach in terms of proper trigger purification and high accuracy achievement, and compared to the state-of-the-art baselines under several commonly-used datasets, our SiferNet has a significant superior performance.
- 9 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 13325-13341
AirWrite: An Aerial Handwriting Trajectory Tracking and Recognition System With mmWave
In the field of human-computer interaction (HCI), handwriting trajectory tracking and recognition have attracted significant attention due to their wide range of applications. However, many existing approaches rely on handheld devices and are highly susceptible to factors such as environmental conditions, location, and writing style. To overcome these limitations, we propose AirWrite, a novel contactless aerial system for handwriting trajectory tracking and recognition using mmWave technology. We introduce a signal clipping method based on the Doppler effect caused by user actions to accurately remove non-handwriting signals in the time domain. Additionally, we analyze power variations within the signal frequency interval to determine the handwriting frequency and employ a band-pass filter to eliminate dynamic environmental noise effectively. Through extensive experiments, we demonstrate that AirWrite can precisely track handwriting trajectories in noisy environments regardless of distance, angle, handwriting speed, character size, or in the presence of obstacles. Furthermore, we present an effective handwritten character recognition method for AirWrite that recognizes alphabets, numbers, and words. AirWrite can achieve an average accuracy of over 96% with only a 34 KB small dataset within 0.15 s for recognition.
- 9 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 13325-13341
AirWrite: An Aerial Handwriting Trajectory Tracking and Recognition System With mmWave
In the field of human-computer interaction (HCI), handwriting trajectory tracking and recognition have attracted significant attention due to their wide range of applications. However, many existing approaches rely on handheld devices and are highly susceptible to factors such as environmental conditions, location, and writing style. To overcome these limitations, we propose AirWrite, a novel contactless aerial system for handwriting trajectory tracking and recognition using mmWave technology. We introduce a signal clipping method based on the Doppler effect caused by user actions to accurately remove non-handwriting signals in the time domain. Additionally, we analyze power variations within the signal frequency interval to determine the handwriting frequency and employ a band-pass filter to eliminate dynamic environmental noise effectively. Through extensive experiments, we demonstrate that AirWrite can precisely track handwriting trajectories in noisy environments regardless of distance, angle, handwriting speed, character size, or in the presence of obstacles. Furthermore, we present an effective handwritten character recognition method for AirWrite that recognizes alphabets, numbers, and words. AirWrite can achieve an average accuracy of over 96% with only a 34 KB small dataset within 0.15 s for recognition.
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2038-2048
GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks
This paper focuses on the transferability problem of adversarial examples towards black-box attack scenarios wherein model information such as the neural network structure is unavailable. To tackle this predicament, we propose a new adversarial example-generating scheme through bridging a data-modal conversion regime to spawn transferable adversarial examples without referring to the substitute model. Three contributions are mainly involved: i) we figure out an integrated framework to produce transferable adversarial examples through resorting to three components, i.e., image-to-graph conversion, perturbation on converted graph and graph-to-image inversion; ii) upon the conversion from image to graph, we pinpoint critical graph characteristics to implement perturbation using gradient-oriented and optimization-oriented adversarial attacks, then, invert the perturbation on graph into the pixel disturbance correspondingly; iii) multi-facet experiments verify the reasonability and effectiveness with the comparison to three baseline methods. Our work has two novelties: first, without referring to the substitute model, our proposed scheme does not need to acquire any information about the victim model in advance; second, we explore the possibility that inferring the adversarial features of image data through drawing support from network/graph science. In addition, we present three key issues worth deeper discussion, along with these open issues, our work deserves more studies in future.
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 2038-2048
GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks
This paper focuses on the transferability problem of adversarial examples towards black-box attack scenarios wherein model information such as the neural network structure is unavailable. To tackle this predicament, we propose a new adversarial example-generating scheme through bridging a data-modal conversion regime to spawn transferable adversarial examples without referring to the substitute model. Three contributions are mainly involved: i) we figure out an integrated framework to produce transferable adversarial examples through resorting to three components, i.e., image-to-graph conversion, perturbation on converted graph and graph-to-image inversion; ii) upon the conversion from image to graph, we pinpoint critical graph characteristics to implement perturbation using gradient-oriented and optimization-oriented adversarial attacks, then, invert the perturbation on graph into the pixel disturbance correspondingly; iii) multi-facet experiments verify the reasonability and effectiveness with the comparison to three baseline methods. Our work has two novelties: first, without referring to the substitute model, our proposed scheme does not need to acquire any information about the victim model in advance; second, we explore the possibility that inferring the adversarial features of image data through drawing support from network/graph science. In addition, we present three key issues worth deeper discussion, along with these open issues, our work deserves more studies in future.
- 23 November 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 36 (4)
TAEffect: Quantifying interaction risks in trust‐enabled communication systems
Summary: The interactive risks of different devices, serving as clients or servers, have increasingly attracted huge attention in various communication systems, such as wireless sensor networks, wireless communication networks, and mobile crowd‐sensing. At present, lots of countermeasures had been proposed and deployed accordingly. Nevertheless, the investigation on the interaction risks between different devices is still very limited to date. In this paper, we propose a novel adverse effect inference mechanism TAEffect for malicious behaviors of devices emerged in various decentralized and open communication systems/networks through network‐percolation theory. At first, four typical malicious interactional behaviors are mapped into four topologies, then, upon which a network influence‐inspired approach is employed to quantify the adverse effect. Finally, multifacet experiments using five real‐world datasets and a synthetic testbed are performed to validate the efficiency and effectiveness. The experimental results show our proposed approach is significant and rational to quantitatively calculate and qualitatively mirror the four kinds of malicious interactional behaviors in diverse misbehavior‐emerged communication systems.
- 23 November 2022
- Published by Wiley in International Journal of Communication Systems
- Vol. 36 (4)
TAEffect: Quantifying interaction risks in trust‐enabled communication systems
Summary: The interactive risks of different devices, serving as clients or servers, have increasingly attracted huge attention in various communication systems, such as wireless sensor networks, wireless communication networks, and mobile crowd‐sensing. At present, lots of countermeasures had been proposed and deployed accordingly. Nevertheless, the investigation on the interaction risks between different devices is still very limited to date. In this paper, we propose a novel adverse effect inference mechanism TAEffect for malicious behaviors of devices emerged in various decentralized and open communication systems/networks through network‐percolation theory. At first, four typical malicious interactional behaviors are mapped into four topologies, then, upon which a network influence‐inspired approach is employed to quantify the adverse effect. Finally, multifacet experiments using five real‐world datasets and a synthetic testbed are performed to validate the efficiency and effectiveness. The experimental results show our proposed approach is significant and rational to quantitatively calculate and qualitatively mirror the four kinds of malicious interactional behaviors in diverse misbehavior‐emerged communication systems.
- Open Access
Private delegated computations using strong isolation
Sensitive computations are now routinely delegated to third-parties. In response, Confidential Computing technologies are being introduced to microprocessors, offering a protected processing environment, which we generically call an isolate, providing confidentiality and integrity guarantees to code and data hosted within -- even in the face of a privileged attacker. Isolates, with an attestation protocol, permit remote third-parties to establish a trusted "beachhead" containing known code and data on an otherwise untrusted machine. Yet, the rise of these technologies introduces many new problems, including: how to ease provisioning of computations safely into isolates; how to develop distributed systems spanning multiple classes of isolate; and what to do about the billions of "legacy" devices without support for Confidential Computing? Tackling the problems above, we introduce Veracruz, a framework that eases the design and implementation of complex privacy-preserving, collaborative, delegated computations among a group of mutually mistrusting principals. Veracruz supports multiple isolation technologies and provides a common programming model and attestation protocol across all of them, smoothing deployment of delegated computations over supported technologies. We demonstrate Veracruz in operation, on private in-cloud object detection on encrypted video streaming from a video camera. In addition to supporting hardware-backed isolates -- like AWS Nitro Enclaves and Arm Confidential Computing Architecture Realms -- Veracruz also provides pragmatic "software isolates" on Armv8-A devices without hardware Confidential Computing capability, using the high-assurance seL4 microkernel and our IceCap framework.
Open AccessPrivate delegated computations using strong isolation
Sensitive computations are now routinely delegated to third-parties. In response, Confidential Computing technologies are being introduced to microprocessors, offering a protected processing environment, which we generically call an isolate, providing confidentiality and integrity guarantees to code and data hosted within -- even in the face of a privileged attacker. Isolates, with an attestation protocol, permit remote third-parties to establish a trusted "beachhead" containing known code and data on an otherwise untrusted machine. Yet, the rise of these technologies introduces many new problems, including: how to ease provisioning of computations safely into isolates; how to develop distributed systems spanning multiple classes of isolate; and what to do about the billions of "legacy" devices without support for Confidential Computing? Tackling the problems above, we introduce Veracruz, a framework that eases the design and implementation of complex privacy-preserving, collaborative, delegated computations among a group of mutually mistrusting principals. Veracruz supports multiple isolation technologies and provides a common programming model and attestation protocol across all of them, smoothing deployment of delegated computations over supported technologies. We demonstrate Veracruz in operation, on private in-cloud object detection on encrypted video streaming from a video camera. In addition to supporting hardware-backed isolates -- like AWS Nitro Enclaves and Arm Confidential Computing Architecture Realms -- Veracruz also provides pragmatic "software isolates" on Armv8-A devices without hardware Confidential Computing capability, using the high-assurance seL4 microkernel and our IceCap framework.
- 8 April 2022
- Published by Springer Nature
- p. 722-730
Contrastive Disentangled Graph Convolutional Network for Weakly-Supervised Classification
- 8 April 2022
- Published by Springer Nature
- p. 722-730
Contrastive Disentangled Graph Convolutional Network for Weakly-Supervised Classification