Shu Wang
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
Shu Wang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Kun Sun
George Mason University, Fairfax, VA, USA
4 shared publications - Brian Choi
Johns Hopkins University, Baltimore, USA
1 shared publication - Di Wu
School of Data and Target Engineering, Information Engineering University, Zhengzhou, China
1 shared publication - Fuli Wang
College of Information Science and Engineering, Northeastern University, Shenyang, 110819, China; State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, 110819, China
1 shared publication - Isabelle Choi
University of California, Los Angeles, Los Angeles, USA
1 shared publication - Jing Xu
Hubei Key Laboratory of Internet of Intelligence, School of Electronics Information and Communications, Huazhong University of Science and Technology, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 442-455
ChainMarks: Securing DNN Watermark with Cryptographic Chain
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 442-455
Open AccessChainMarks: Securing DNN Watermark with Cryptographic Chain
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2281-2295
Dye4AI: Assuring Data Boundary on Generative AI Services
Generative artificial intelligence (AI) is versatile for various applications, but security and privacy concerns with third-party AI vendors hinder its broader adoption in sensitive scenarios. Hence, it is essential for users to validate the AI trustworthiness and ensure the security of data boundaries. In this paper, we present a dye testing system named Dye4AI, which injects crafted trigger data into human-AI dialogue and observes AI responses towards specific prompts to diagnose data flow in AI model evolution. Our dye testing procedure contains 3 stages: trigger generation, trigger insertion, and trigger retrieval. First, to retain both uniqueness and stealthiness, we design a new trigger that transforms a pseudo-random number to a intelligible format. Second, with a custom-designed three-step conversation strategy, we insert each trigger item into dialogue and confirm the model memorizes the new trigger knowledge in the current session. Finally, we routinely try to recover triggers with specific prompts in new sessions, as triggers can present in new sessions only if AI vendors leverage user data for model fine-tuning. Extensive experiments on six LLMs demonstrate our dye testing scheme is effective in ensuring the data boundary, even for models with various architectures and parameter sizes. Also, larger and premier models tend to be more suitable for Dye4AI, e.g., trigger can be retrieved in OpenLLaMa-13B even with only 2 insertions per trigger item. Moreover, we analyze the prompt selection in dye testing, providing insights for future testing systems on generative AI services.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2281-2295
Open AccessDye4AI: Assuring Data Boundary on Generative AI Services
Generative artificial intelligence (AI) is versatile for various applications, but security and privacy concerns with third-party AI vendors hinder its broader adoption in sensitive scenarios. Hence, it is essential for users to validate the AI trustworthiness and ensure the security of data boundaries. In this paper, we present a dye testing system named Dye4AI, which injects crafted trigger data into human-AI dialogue and observes AI responses towards specific prompts to diagnose data flow in AI model evolution. Our dye testing procedure contains 3 stages: trigger generation, trigger insertion, and trigger retrieval. First, to retain both uniqueness and stealthiness, we design a new trigger that transforms a pseudo-random number to a intelligible format. Second, with a custom-designed three-step conversation strategy, we insert each trigger item into dialogue and confirm the model memorizes the new trigger knowledge in the current session. Finally, we routinely try to recover triggers with specific prompts in new sessions, as triggers can present in new sessions only if AI vendors leverage user data for model fine-tuning. Extensive experiments on six LLMs demonstrate our dye testing scheme is effective in ensuring the data boundary, even for models with various architectures and parameter sizes. Also, larger and premier models tend to be more suitable for Dye4AI, e.g., trigger can be retrieved in OpenLLaMa-13B even with only 2 insertions per trigger item. Moreover, we analyze the prompt selection in dye testing, providing insights for future testing systems on generative AI services.
- Open Access
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1186-1199
BinGo: Identifying Security Patches in Binary Code with Graph Representation Learning
A timely software update is vital to combat the increasing security vulnerabilities. However, some software vendors may secretly patch their vulnerabilities without creating CVE entries or even describing the security issue in their change log. Thus, it is critical to identify these hidden security patches and defeat potential N-day attacks. Researchers have employed various machine learning techniques to identify security patches in open-source software, leveraging the syntax and semantic features of the software changes and commit messages. However, all these solutions cannot be directly applied to the binary code, whose instructions and program flow may dramatically vary due to different compilation configurations. In this paper, we propose BinGo, a new security patch detection system for binary code. The main idea is to present the binary code as code property graphs to enable a comprehensive understanding of program flow and perform a language model over each basic block of binary code to catch the instruction semantics. BinGo consists of four phases, namely, patch data pre-processing, graph extraction, embedding generation, and graph representation learning. Due to the lack of an existing binary security patch dataset, we construct such a dataset by compiling the pre-patch and post-patch source code of the Linux kernel. Our experimental results show BinGo can achieve up to 80.77% accuracy in identifying security patches between two neighboring versions of binary code. Moreover, BinGo can effectively reduce the false positives and false negatives caused by the different compilers and optimization levels.
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1186-1199
Open AccessBinGo: Identifying Security Patches in Binary Code with Graph Representation Learning
A timely software update is vital to combat the increasing security vulnerabilities. However, some software vendors may secretly patch their vulnerabilities without creating CVE entries or even describing the security issue in their change log. Thus, it is critical to identify these hidden security patches and defeat potential N-day attacks. Researchers have employed various machine learning techniques to identify security patches in open-source software, leveraging the syntax and semantic features of the software changes and commit messages. However, all these solutions cannot be directly applied to the binary code, whose instructions and program flow may dramatically vary due to different compilation configurations. In this paper, we propose BinGo, a new security patch detection system for binary code. The main idea is to present the binary code as code property graphs to enable a comprehensive understanding of program flow and perform a language model over each basic block of binary code to catch the instruction semantics. BinGo consists of four phases, namely, patch data pre-processing, graph extraction, embedding generation, and graph representation learning. Due to the lack of an existing binary security patch dataset, we construct such a dataset by compiling the pre-patch and post-patch source code of the Linux kernel. Our experimental results show BinGo can achieve up to 80.77% accuracy in identifying security patches between two neighboring versions of binary code. Moreover, BinGo can effectively reduce the false positives and false negatives caused by the different compilers and optimization levels.
- Open Access
- 17 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (EICS) , 1-19
Having Difficulty Understanding Manuals? Automatically Converting User Manuals into Instructional Videos
While users tend to perceive instructional videos as an experience rather than a lesson with a set of instructions, instructional videos are more effective and appealing than textual user manuals and eliminate the ambiguity in text-based descriptions. However, most software vendors only offer document manuals that describe how to install and use their software, leading burden for non-professionals to comprehend the instructions. In this paper, we present a framework called M2V to generate instructional videos automatically based on the provided instructions and images in user manuals. M2V is a two-step framework. First, an action sequence is extracted from the given user manual via natural language processing and computer vision techniques. Second, M2V operates the software sequentially based on the extracted actions; meanwhile, the operation procedure is recorded into an instructional video. We evaluate the usability of automatically generated instructional videos via user studies and an online survey. The evaluation results show, with our toolkit, the generated instructional videos can better assist non-professional end users with the software operations. Moreover, more than 85% of survey participants prefer to use the instructional videos rather than the original user manuals.
- 17 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (EICS) , 1-19
Open AccessHaving Difficulty Understanding Manuals? Automatically Converting User Manuals into Instructional Videos
While users tend to perceive instructional videos as an experience rather than a lesson with a set of instructions, instructional videos are more effective and appealing than textual user manuals and eliminate the ambiguity in text-based descriptions. However, most software vendors only offer document manuals that describe how to install and use their software, leading burden for non-professionals to comprehend the instructions. In this paper, we present a framework called M2V to generate instructional videos automatically based on the provided instructions and images in user manuals. M2V is a two-step framework. First, an action sequence is extracted from the given user manual via natural language processing and computer vision techniques. Second, M2V operates the software sequentially based on the extracted actions; meanwhile, the operation procedure is recorded into an instructional video. We evaluate the usability of automatically generated instructional videos via user studies and an online survey. The evaluation results show, with our toolkit, the generated instructional videos can better assist non-professional end users with the software operations. Moreover, more than 85% of survey participants prefer to use the instructional videos rather than the original user manuals.
- Open Access
- 1 January 2024
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2024 (1)
Heterogeneous UAV Swarm Collaborative Search Mission Path Optimization Scheme for Dynamic Targets
To solve the problem of collaborative search mission planning (CSMP) for a heterogeneous unmanned aerial vehicle (UAV) swarm for dynamic targets, this paper proposes a new CSMP scheme for a heterogeneous UAV swarm. First, a new polar coordinate system motion method is used to establish the UAV motion model and decision input solution model, which effectively solves the path‐unified coding problem of a heterogeneous UAV swarm. Then, in the mission area, a dynamically updated multisearch situation map model is established. Finally, to improve the global searching capability of a UAV, an improved path optimization algorithm PSO‐Rolling Horizon Control (PSO‐RHC) is designed. Multiple Monte Carlo simulations are performed for three time‐sensitive moving target types and three constraint types. The simulation results show that the task execution efficiency indexes of the proposed scheme for the decision input solution model, pheromone update mechanism, and optimization algorithm are improved by 188%, 72%, and 102%, respectively, and the overall performance is improved by 227%.
- 1 January 2024
- Published by Wiley in International Journal of Aerospace Engineering
- Vol. 2024 (1)
Open AccessHeterogeneous UAV Swarm Collaborative Search Mission Path Optimization Scheme for Dynamic Targets
To solve the problem of collaborative search mission planning (CSMP) for a heterogeneous unmanned aerial vehicle (UAV) swarm for dynamic targets, this paper proposes a new CSMP scheme for a heterogeneous UAV swarm. First, a new polar coordinate system motion method is used to establish the UAV motion model and decision input solution model, which effectively solves the path‐unified coding problem of a heterogeneous UAV swarm. Then, in the mission area, a dynamically updated multisearch situation map model is established. Finally, to improve the global searching capability of a UAV, an improved path optimization algorithm PSO‐Rolling Horizon Control (PSO‐RHC) is designed. Multiple Monte Carlo simulations are performed for three time‐sensitive moving target types and three constraint types. The simulation results show that the task execution efficiency indexes of the proposed scheme for the decision input solution model, pheromone update mechanism, and optimization algorithm are improved by 188%, 72%, and 102%, respectively, and the overall performance is improved by 227%.
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1930529X,p. 1-5
Optimization of Cooperative Spectrum Sensing in Ad-Hoc Cognitive Radio Networks
Spectrum sensing is an essential functionality of cognitive radio networks (CRN). Among existing spectrum sensing methods, cooperative spectrum sensing is the best one which can achieve superior sensing performance by introducing spatial diversity of sensing data sources. Such cooperation also introduces additional information exchanging which leads to extra power consumption and reporting delay. In this paper, the optimal sensing performance problem is formulated as a nonlinear binary integer programming problem to find suitable cooperative nodes minimizing the average detection Bayesian risk. The binary particle swarm optimization (BPSO) algorithm is adopted to obtain suboptimal solutions to cooperative nodes. Computer simulations show that the proposed scheme can significantly improve the sensing performance compared with the case that all neighboring nodes participate in sensing without discrimination under different scenarios.
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1930529X,p. 1-5
Optimization of Cooperative Spectrum Sensing in Ad-Hoc Cognitive Radio Networks
Spectrum sensing is an essential functionality of cognitive radio networks (CRN). Among existing spectrum sensing methods, cooperative spectrum sensing is the best one which can achieve superior sensing performance by introducing spatial diversity of sensing data sources. Such cooperation also introduces additional information exchanging which leads to extra power consumption and reporting delay. In this paper, the optimal sensing performance problem is formulated as a nonlinear binary integer programming problem to find suitable cooperative nodes minimizing the average detection Bayesian risk. The binary particle swarm optimization (BPSO) algorithm is adopted to obtain suboptimal solutions to cooperative nodes. Computer simulations show that the proposed scheme can significantly improve the sensing performance compared with the case that all neighboring nodes participate in sensing without discrimination under different scenarios.
- 15 December 2007
- Published by Science Alert in Information Technology Journal
- Vol. 7 (1) , 185-189
Minimax Probability Machine with Genetic Feature Optimized for Intrusion Detection
Minimax Probability Machine with Genetic Feature Optimized for Intrusion Detection
- 15 December 2007
- Published by Science Alert in Information Technology Journal
- Vol. 7 (1) , 185-189
Minimax Probability Machine with Genetic Feature Optimized for Intrusion Detection
Minimax Probability Machine with Genetic Feature Optimized for Intrusion Detection
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 3095-3100
Quality Prediction and Control of Injection Molding Process using Multistage MWGRNN Method
A multistage moving window generalized regression neural network (GRNN) was demonstrated to injection molding batch process. Firstly analyzing the changes of process correlation can lead to effective division of a process into several "operation" stages, in good agreement with process knowledge. Then the nonlinearly and dynamic relationship between process variables and final qualities was made at different stages, and a multistage online quality prediction model was built. In addition, a closed-loop quality control system is proposed. Application has demonstrated that this method can not only give a valid quality prediction, but also effectively carry on quality closed-loop control
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 3095-3100
Quality Prediction and Control of Injection Molding Process using Multistage MWGRNN Method
A multistage moving window generalized regression neural network (GRNN) was demonstrated to injection molding batch process. Firstly analyzing the changes of process correlation can lead to effective division of a process into several "operation" stages, in good agreement with process knowledge. Then the nonlinearly and dynamic relationship between process variables and final qualities was made at different stages, and a multistage online quality prediction model was built. In addition, a closed-loop quality control system is proposed. Application has demonstrated that this method can not only give a valid quality prediction, but also effectively carry on quality closed-loop control