Modern enterprise networks heavily rely on network functions for advanced traffic processing such as deep packet inspection, traffic classification, and load balancing. Recent advances in Network Function Virtualisation (NFV) have pushed forward the paradigm of migrating in-house network functions to third-party cloud providers as software-based services for reduced cost and increased scalability. Despite its benefits, such a new service model also raises security and privacy concerns, as traffic is now redirected and processed in an untrusted environment. My research in this area focuses on two directions: 1) enabling ubiquitous network functions over encrypted network traffic via practical cryptographic protocols [IEEE INFOCOM'16], [IEEE TDSC'21] or confidential computing [ACM CCS'19], [NDSS'21], 2) providing assurance for network function execution [IEEE ICNP'16], [ACM/IEEE ToN'18].

• [IEEE TDSC'21]
  Practical Encrypted Network Traffic Pattern Matching for Secure Middleboxes
  Shangqi Lai, Xingliang Yuan, Shi-Feng Sun, Joseph Liu, Ron Steinfeld, Amin Sakzad, and Dongxi Liu
  IEEE Transactions on Dependable and Secure Computing, In Press, 2021.
• [ISOC NDSS'21]
  OblivSketch: Oblivious Network Measurement as a Cloud Service
  Shangqi Lai, Xingliang Yuan, Joseph Liu, Xun Yi, Qi Li, Dongxi Liu, and Surya Nepal
  In the Network and Distributed System Security Symposium, 2021 (Acceptance ratio: 15%).
• [ACM CCS'19]
  LightBox: Full-stack Protected Stateful Middlebox at Lightning Speed
  Huayi Duan, Cong Wang, Xingliang Yuan, Yajin Zhou, Qian Wang, and Kui Ren
  In the 26th ACM Conference on Computer and Communications Security, 2019 (Acceptance ratio: 16%).
• [ACM/IEEE ToN'18]
  Assuring String Pattern Matching in Outsourced Middleboxes
  Xingliang Yuan, Huayi Duan, and Cong Wang
  IEEE/ACM Transactions on Networking (ToN), In Press, 2018.
• [IEEE Network'18]
  Towards Secure Outsourced Middlebox Services: Practices, Challenges, and Beyond
  Cong Wang, Xingliang Yuan, Cui Yong, and Kui Ren
  IEEE Network Magazine (IEEE Network), vol. 32, no. 1, page 166-171, 2018.
• [IEEE ICNP'16]
  Bringing Execution Assurances of Pattern Matching in Outsourced Middleboxes
  Xingliang Yuan, Huayi Duan, and Cong Wang
  In the 24th IEEE International Conference on Network Protocols, 2016 (Acceptance ratio: 20%).
• [IEEE INFOCOM'16]
  Privacy-preserving Deep Packet Inspection in Outsourced Middleboxes
  Xingliang Yuan, Xinyu Wang, Jianxiong Lin, and Cong Wang
  In the 35th International Conference on Computer Communications, 2016 (Acceptance ratio: 19%).

Due to increasing popularity and rapid advancement of deep learning, public cloud service providers are promoting Machine Learning as a Service (MLaaS), e.g., AWS SageMaker. In the meantime, security and privacy issues of machine learning models, algorithms, and services are not fully understood and addressed in academia and industry. My research in this area focuses on three directions: 1) designing lightweight privacy-preserving machine learning systems [ESORICS'21], [IEEE TIFS'21], [IEEE TDSC'22-a], [IOS JCS], 2) investigating adversarial attacks and defenses on emerging ML paradigm like Graph Neural Networks (GNN) [ACM AsiaCCS'21], [IEEE ICDM'21], [ACM CIKM'21], transfer learning [IEEE TDSC'22-b], and 3) devising secure and efficient federated learning algorithms [IEEE INFOCOM'22], [IEEE TDSC'22-c].

• [IOS JCS]
  Deep Learning-Based Medical Diagnostic Services: A Secure, Lightweight, and Accurate Realization
  Xiaoning Liu, Yifeng Zheng, Xingliang Yuan, and Xun Yi
  Journal of Computer Security (JCS), Accepted, 2022.
• [IEEE TDSC'22-c]
  Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization
  Yifeng Zheng, Shangqi Lai, Yi Liu, Xingliang Yuan, Xun Yi, and Cong Wang
  IEEE Transactions on Dependable and Secure Computing, Accepted, 2022.
• [IEEE TDSC'22-b]
  Defeating Misclassification Attacks Against Transfer Learning
  Bang Wu, Shuo Wang, Xingliang Yuan, Cong Wang, Carsten Rudolph, Xiangwen Yang
  IEEE Transactions on Dependable and Secure Computing, Accepted, 2022.
• [IEEE TDSC'22-a]
  Securely Outsourcing Neural Network Inference to the Cloud with Lightweight Techniques
  Xiaoning Liu, Yifeng Zheng, Xingliang Yuan, and Xun Yi
  IEEE Transactions on Dependable and Secure Computing, Accepted, 2022.
• [IEEE TIFS'21]
  Leia: A Lightweight Cryptographic Neural Network Inference System at the Edge
  Xiaoning Liu, Bang Wu, Xingliang Yuan, and Xun Yi
  IEEE Transactions on Information Forensics and Security, Accepted, 2021.
• [IEEE INFOCOM'22]
  The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
  Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li
  In the 41st International Conference on Computer Communications, Accepted, 2022 (Acceptance ratio: 19.9%).
• [ACM AsiaCCS'22]
  Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realisation
  Bang Wu, Xiangwen Yang, Shirui Pan, and Xingliang Yuan
  In the 17th ACM ASIA Conference on Computer and Communications Security, 2022 (First round acceptance ratio: 15%).
• [IEEE ICDM'21]
  Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications
  Bang Wu, Xiangwen Yang, Shirui Pan, and Xingliang Yuan
  In the IEEE International Conference on Data Mining, 2021.
• [ACM CIKM'21]
  Projective Ranking: A Transferable Evasion Attack Method on Graph Neural Networks
  He Zhang, Bang Wu, Xiangwen Yang, Chuan Zhou, Shuo Wang, Xingliang Yuan, and Shirui Pan
  In the 30th ACM International Conference on Information and Knowledge Management, 2021.
• [ESORICS'21]
  MediSC: Towards Secure and Lightweight Deep Learning as a Medical Diagnostic Service
  Xiaoning Liu, Yifeng Zheng, Xingliang Yuan, and Xun Yi
  In the 26th European Symposium on Research in Computer Security, 2021 (Best Paper Award, Acceptance ratio: 21%).

Encrypted databases are designed to fight against massive data breaches. They preserve database query functionalities over encrypted data directly without decryption. My research in this area focuses on four aspects: 1) enabling rich queries for encrypted databases [ESORICS'15], [IEEE TMM'16], [IEEE TIFS'17], [ACM AsiaCCS'19], 2) developing encrypted NoSQL data stores [ACM AsiaCCS'16], [ACM AsiaCCS'17], 3) designing efficient encrypted search schemes with less leakage [ACM CCS'18], [ACNS'20], [ACNS'21], [NDSS'21], and 4) exploring hardening techniques for encrypted databases [IEEE INFOCOM'19], [IEEE TKDE'21], [IEEE TIFS'21].

• [IEEE TIFS'21]
  Interpreting and Mitigating Leakage-abuse Attacks in Searchable Symmetric Encryption
  Lei Xu, Huayi Duan, Anxin Zhou, Xingliang Yuan, and Cong Wang
  IEEE Transactions on Information Forensics and Security, Accepted, 2021.
• [IEEE TKDE'21]
  ShieldDB: An Encrypted Document Database with Padding Countermeasures
  Viet Vo, Xingliang Yuan, Shi-Feng Sun, Joseph Liu, Surya Nepal, and Cong Wang
  IEEE Transactions on Knowledge and Data Engineering, Accepted, 2021.
• [ISOC NDSS'21]
  Practical Non-Interactive Searchable Encryption with Forward and Backward Privacy
  Shi-Feng Sun, Ron Steinfeld, Shangqi Lai, Xingliang Yuan, Amin Sakzad, Joseph Liu, Surya Nepal, and Dawu Gu
  In the Network and Distributed System Security Symposium, 2021 (Acceptance ratio: 15%).
• [ACNS'21]
  Towards Efficient and Strong Backward Private Searchable Encryption with Secure Enclaves
  Viet Vo, Shangqi Lai, Xingliang Yuan, Joseph Liu, and Surya Nepal
  In the 19th International Conference on Applied Cryptography and Network Security, 2021 (First round acceptance ratio: 13/77= 16.8%).
• [ACNS'20]
  Accelerating Forward and Backward Private Searchable Encryption Using Trusted Execution
  Viet Vo, Shangqi Lai, Xingliang Yuan, Shi-Feng Sun, Surya Nepal, and Joseph K. Liu
  In the 18th International Conference on Applied Cryptography and Network Security, 2020 (Acceptance ratio: 21%).
• [ACM AsiaCCS'19]
  GraphSE^2: An Encrypted Graph Database for Privacy-Preserving Social Search
  Shangqi Lai, Xingliang Yuan, Shi-Feng Sun, Joseph K. Liu, Yuhong Liu, and Dongxi Liu
  In the 14th ACM Asia Conference on Computer and Communications Security, 2019 (Acceptance ratio: 17%).
• [IEEE INFOCOM'19]
  Hardening Database Padding for Searchable Encryption
  Lei Xu, Xingliang Yuan, Cong Wang, Qian Wang, and Chungen Xu
  In the 38th International Conference on Computer Communications, 2019 (Acceptance ratio: 19.7%).
• [ACM CCS'18]
  Practical Backward-Secure Searchable Encryption from Symmetric Puncturable Encryption
  Shi-Feng Sun, Xingliang Yuan, Joseph K. Liu, Ron Steinfeld, Amin Sakzad, Viet Vo, and Surya Nepal
  In the 25th ACM Conference on Computer and Communications Security, 2018 (Acceptance ratio: 134/809 = 16.6%).
• [IEEE TIFS'17]
  Privacy-preserving Similarity Joins Over Encrypted Data
  Xingliang Yuan, Xinyu Wang, Chenyun Yu, and Sarana Nutanong
  IEEE Transactions on Information Forensics and Security (TIFS), vol. 12, no. 11, page 2763-2775, 2017.
• [ACM AsiaCCS'17]
  EncKV: An Encrypted Key-value Store with Rich Queries
  Xingliang Yuan, Yu Guo, Xinyu Wang, Cong Wang, Baochun Li, and Xiaohua Jia
  In the 12th ACM Asia Conference on Computer and Communications Security, 2017 (Acceptance ratio: 18.6%) Extended Version in IEEE TPDS.
• [IEEE TMM'16]
  Enabling Secure and Fast Indexing for Privacy-assured Healthcare Monitoring via Compressive Sensing
  Xingliang Yuan, Xinyu Wang, Cong Wang, and Kui Ren
  IEEE Transactions on Multimedia (TMM), vol. 18, no. 10, page 2002-2014, 2016.
• [ACM AsiaCCS'16]
  Building an Encrypted, Distributed, and Searchable Key-value Store
  Xingliang Yuan, Xinyu Wang, Cong Wang, Chen Qian, and Jianxiong Lin
  In the 11th ACM Asia Conference on Computer and Communications Security, 2017 (Acceptance ratio: 20.9%).
• [ESORICS'15]
  Enabling Privacy-assured Similarity Retrieval over Millions of Encrypted Records
  Xingliang Yuan, Helei Cui, Xinyu Wang, and Cong Wang
  In the 20th European Symposium on Research in Computer Security, 2015 (Acceptance ratio: 19.8%).