Shengzhi Zhang
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
Shengzhi Zhang has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
Peng Liu
The Pennsylvania State University
10 shared publicationsXiaoqi Jia
State Key Laboratory of Information Security, Institute of Information Engineering, CAS, Beijing, China
10 shared publications- Kai Chen
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
4 shared publications - Xiaoqi Jia
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
4 shared publications - Peizhuo Lv
Nanyang technological university, Singapore, Singapore
3 shared publications - Peng Liu
State Key Laboratory of Pathogen and Biosecurity, Academy of Military Medical Sciences, Beijing 100071, China
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 137-151
PaDEx: Addressing Mobile GPU MMIO Risks via P rohibition a nd D elayed Ex ecution
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 137-151
Open AccessPaDEx: Addressing Mobile GPU MMIO Risks via P rohibition a nd D elayed Ex ecution
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (4) , 7908-7925
ERASE: Bypassing Collaborative Detection of AI Counterfeit via Comprehensive Artifacts Elimination
The rapid advancement of AI-Generated Images (AIGI) has amplified concerns about increasingly undetectable deepfakes. Recent adversarial techniques further worsen this problem by enhancing the imperceptibility of synthetic forgeries to both human viewers and automated detection systems. To simulate realistic adversaries and expose detection vulnerabilities, AI-Generated Image Stealth (AIGI-S) methods specifically aim to make synthetic images harder to detect. However, existing AIGI-S approaches often lack universality and transferability across diverse detection models—especially in collaborative detection settings—and tend to prioritize machine deception over human perceptual fidelity, resulting in visible artifacts. Inspired by real-world antique painting forgery, we propose ERASE (comprehensivE counteRfeit ArtifactS Elimination), a stealth-oriented optimization framework designed for multi-detector environments. ERASE comprehensively suppresses generative artifacts and incorporates a perceptual optimization objective to improve deception against both detection algorithms and human examiners. Extensive evaluations across eight distinct generative subsets from the GenImage benchmark and fifteen detection models demonstrate that ERASE delivers substantially improved attack performance—improving single-detector evasion by +10.5% and collaborative detection evasion by +17.9%—while preserving high image quality.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (4) , 7908-7925
ERASE: Bypassing Collaborative Detection of AI Counterfeit via Comprehensive Artifacts Elimination
The rapid advancement of AI-Generated Images (AIGI) has amplified concerns about increasingly undetectable deepfakes. Recent adversarial techniques further worsen this problem by enhancing the imperceptibility of synthetic forgeries to both human viewers and automated detection systems. To simulate realistic adversaries and expose detection vulnerabilities, AI-Generated Image Stealth (AIGI-S) methods specifically aim to make synthetic images harder to detect. However, existing AIGI-S approaches often lack universality and transferability across diverse detection models—especially in collaborative detection settings—and tend to prioritize machine deception over human perceptual fidelity, resulting in visible artifacts. Inspired by real-world antique painting forgery, we propose ERASE (comprehensivE counteRfeit ArtifactS Elimination), a stealth-oriented optimization framework designed for multi-detector environments. ERASE comprehensively suppresses generative artifacts and incorporates a perceptual optimization objective to improve deception against both detection algorithms and human examiners. Extensive evaluations across eight distinct generative subsets from the GenImage benchmark and fifteen detection models demonstrate that ERASE delivers substantially improved attack performance—improving single-detector evasion by +10.5% and collaborative detection evasion by +17.9%—while preserving high image quality.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (4) , 1608-1621
FlexClave: An Extensible and Secure Trusted Execution Environment Framework
As computer system software stacks become increasingly complex, the associated security risks also escalate. Trusted Execution Environments (TEEs) have emerged as a mainstream security solution to enhance system security. TEEs can be categorized into user-level TEEs, OS-level TEEs, and hybrid TEEs. However, these TEEs typically possess fixed security boundaries and isolation domains, limiting their adaptability to varying security requirements and dynamic scenarios. Moreover, the design of Trusted Computing Base (TCB) components in TEE frameworks often operates at the highest privilege levels of the architecture. This concentration of critical code at the highest privilege level increases the whole platform’s security risk due to the growing amount of code as more security functions are added. In this paper, we propose FlexClave, an extensible and secure TEE framework designed to address these issues. FlexClave leverages hardware primitives to create secure isolation boundaries tailored to different use cases. Additionally, our framework distributes TCB components across various privilege levels, reducing the concentration of security functions at the highest privilege levels and mitigating the risks associated with running extensive code in a single, highly privileged context. We implement two prototypes on ARMv9-A Fixed Virtual Platform and ARMv8 RK3399 SoC, each with two use cases (container and virtual machine), to evaluate the system’s security and performance.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (4) , 1608-1621
FlexClave: An Extensible and Secure Trusted Execution Environment Framework
As computer system software stacks become increasingly complex, the associated security risks also escalate. Trusted Execution Environments (TEEs) have emerged as a mainstream security solution to enhance system security. TEEs can be categorized into user-level TEEs, OS-level TEEs, and hybrid TEEs. However, these TEEs typically possess fixed security boundaries and isolation domains, limiting their adaptability to varying security requirements and dynamic scenarios. Moreover, the design of Trusted Computing Base (TCB) components in TEE frameworks often operates at the highest privilege levels of the architecture. This concentration of critical code at the highest privilege level increases the whole platform’s security risk due to the growing amount of code as more security functions are added. In this paper, we propose FlexClave, an extensible and secure TEE framework designed to address these issues. FlexClave leverages hardware primitives to create secure isolation boundaries tailored to different use cases. Additionally, our framework distributes TCB components across various privilege levels, reducing the concentration of security functions at the highest privilege levels and mitigating the risks associated with running extensive code in a single, highly privileged context. We implement two prototypes on ARMv9-A Fixed Virtual Platform and ARMv8 RK3399 SoC, each with two use cases (container and virtual machine), to evaluate the system’s security and performance.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5135-5149
FedWM: Data-Free Watermarking for Model Ownership Protection in Federated Learning
The widespread adoption of federated learning has been driven by growing demands for privacy protection in model training. Federated learning enables multiple clients to collaboratively train a global model coordinated by a central server without sharing their raw data. However, when distributing the global model to clients, the central server faces significant security risks from malicious clients who may steal and misuse the model, thereby compromising its ownership. While existing watermarking techniques typically rely on main task data for ownership protection, their application in federated learning is limited since the server lacks access to this data, which remains with the clients. To address this challenge, we propose a novel data-free watermarking method. We utilize substitute data unrelated to the main task and improve efficiency by filtering out redundant samples. To optimize the watermarking process, we introduce a logits alignment-based optimization strategy that uses the substitute dataset with watermark triggers for effective embedding. Additionally, we propose a dynamic optimization algorithm to balance the trade-off between watermark embedding and main task. We comprehensively evaluate our approach across four datasets, four model architectures, and three mainstream deep learning tasks. Our experimental results demonstrate nearly perfect watermark performance while maintaining minimal impact on the main task. Notably, our watermarking method proves resistant to existing backdoor detection techniques, establishing its effectiveness, robustness and stealthiness.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5135-5149
FedWM: Data-Free Watermarking for Model Ownership Protection in Federated Learning
The widespread adoption of federated learning has been driven by growing demands for privacy protection in model training. Federated learning enables multiple clients to collaboratively train a global model coordinated by a central server without sharing their raw data. However, when distributing the global model to clients, the central server faces significant security risks from malicious clients who may steal and misuse the model, thereby compromising its ownership. While existing watermarking techniques typically rely on main task data for ownership protection, their application in federated learning is limited since the server lacks access to this data, which remains with the clients. To address this challenge, we propose a novel data-free watermarking method. We utilize substitute data unrelated to the main task and improve efficiency by filtering out redundant samples. To optimize the watermarking process, we introduce a logits alignment-based optimization strategy that uses the substitute dataset with watermark triggers for effective embedding. Additionally, we propose a dynamic optimization algorithm to balance the trade-off between watermark embedding and main task. We comprehensively evaluate our approach across four datasets, four model architectures, and three mainstream deep learning tasks. Our experimental results demonstrate nearly perfect watermark performance while maintaining minimal impact on the main task. Notably, our watermarking method proves resistant to existing backdoor detection techniques, establishing its effectiveness, robustness and stealthiness.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 8553-8568
Unveiling the Backdoor’s Suppression Effect for Backdoor Defence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 8553-8568
Unveiling the Backdoor’s Suppression Effect for Backdoor Defence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1244-1259
AI-Shielder: Exploiting Backdoors to Defend Against Adversarial Attacks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1244-1259
AI-Shielder: Exploiting Backdoors to Defend Against Adversarial Attacks
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1709-1723
RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1709-1723
Open AccessRAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-87
Towards comprehensive protection for OpenFlow controllers
OpenFlow has recently emerged as a powerful paradigm to help build dynamic, adaptive and agile networks. By decoupling control plane from data plane, OpenFlow allows network operators to program a centralized intelligence, OpenFlow controller, to manage network-wide traffic flows to meet the changing needs. However, from the security's point of view, a buggy or even malicious controller could compromise the control logic, and then the entire network. Even worse, the recent attack Stuxnet on industrial control systems also indicates the similar, severe threat to OpenFlow controllers from the commercial operating systems they are running on. In this paper, we comprehensively studied the attack vectors against the OpenFlow critical component, controller, and proposed a cross layer diversity approach that enables OpenFlow controllers to detect attacks, corruptions, failures, and then automatically continue correct execution. Case studies demonstrate that our approach can protect OpenFlow controllers from threats coming from compromised operating systems and themselves.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-87
Towards comprehensive protection for OpenFlow controllers
OpenFlow has recently emerged as a powerful paradigm to help build dynamic, adaptive and agile networks. By decoupling control plane from data plane, OpenFlow allows network operators to program a centralized intelligence, OpenFlow controller, to manage network-wide traffic flows to meet the changing needs. However, from the security's point of view, a buggy or even malicious controller could compromise the control logic, and then the entire network. Even worse, the recent attack Stuxnet on industrial control systems also indicates the similar, severe threat to OpenFlow controllers from the commercial operating systems they are running on. In this paper, we comprehensively studied the attack vectors against the OpenFlow critical component, controller, and proposed a cross layer diversity approach that enables OpenFlow controllers to detect attacks, corruptions, failures, and then automatically continue correct execution. Case studies demonstrate that our approach can protect OpenFlow controllers from threats coming from compromised operating systems and themselves.
- 25 November 2016
- Published by Springer Nature
- p. 361-375
A Comprehensive Study of Co-residence Threat in Multi-tenant Public PaaS Clouds
- 25 November 2016
- Published by Springer Nature
- p. 361-375
A Comprehensive Study of Co-residence Threat in Multi-tenant Public PaaS Clouds
- 9 September 2016
- Published by Springer Nature
- p. 3-20
Analyzing Android Repackaged Malware by Decoupling Their Event Behaviors
- 9 September 2016
- Published by Springer Nature
- p. 3-20
Analyzing Android Repackaged Malware by Decoupling Their Event Behaviors