Zerui Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zerui Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yan Liu
Concordia University
6 shared publications Jun Huang
Department of Electrical and Computer Engineering, Concordia University Montréal
2 shared publications- Abdelwahab Hamou-Lhadj
Concordia University
1 shared publication - Abishek Arumugam Thiruselvi
Concordia University, Montreal, Canada
1 shared publication - Ding Li
Concordia University
1 shared publication - Jun Huang
Electrical and Computer Engineering (ECE) Department of Gina Cody School of Engineering and Computer Science, Concordia University, Montreal, Quebec, Canada
1 shared publication
Latest Publications
- 19 May 2026
- Published by Springer Nature
- p. 470-485
The Role of Provenance Modeling in Tracing and Reproducing Explainable AI Pipelines
- 19 May 2026
- Published by Springer Nature
- p. 470-485
The Role of Provenance Modeling in Tracing and Reproducing Explainable AI Pipelines
- Open Access
- 5 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Joint Spatiotemporal Adversarial Attacks on Video Transformer Models Through XAI-guided Perturbation
The widespread deployment of video transformer models in action recognition systems necessitates a comprehensive understanding of their vulnerability to adversarial attacks. Unlike traditional CNN-based video models, transformers process spatiotemporal dependencies through self-attention mechanisms, creating a different vulnerability profile to adversarial attacks. This study presents an investigation of adversarial robustness in video transformers. We develop a novel joint spatiotemporal attack method that precisely targets the attention mechanisms of video transformers. By simultaneously perturbing both spatial and temporal features, our method achieves a 76.30% in ASR on the Kinetics-400 dataset, outperforming frame-wise attacks and state-of-the-art query-based attacks. To interpret the mechanisms underlying these attacks, we introduce quantitative metrics based on Explainable AI (XAI) analysis. Spatial analysis reveals systematic disruption of attention patterns, with adversarial examples showing median SSIM scores of 0.353. Temporal correlation analysis also demonstrates severe degradation in attention coherence across frame sequences. Through experiments comparing previous attack methods, including common corruptions benchmark, frame-wise attacks, sparse attacks, and recent V-BAD attacks, we demonstrate that our proposed method is more effective in transformer-based video models. This study further examines the adversarial training strategy against the selected attacks. To promote reproducibility and facilitate future research, we provide our methods and analysis tools through a public GitHub repository. These findings underscore the effectiveness of jointly considering spatial and temporal dimensions when developing adversarial attack strategies and defense mechanisms for video AI models.
- 5 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessJoint Spatiotemporal Adversarial Attacks on Video Transformer Models Through XAI-guided Perturbation
The widespread deployment of video transformer models in action recognition systems necessitates a comprehensive understanding of their vulnerability to adversarial attacks. Unlike traditional CNN-based video models, transformers process spatiotemporal dependencies through self-attention mechanisms, creating a different vulnerability profile to adversarial attacks. This study presents an investigation of adversarial robustness in video transformers. We develop a novel joint spatiotemporal attack method that precisely targets the attention mechanisms of video transformers. By simultaneously perturbing both spatial and temporal features, our method achieves a 76.30% in ASR on the Kinetics-400 dataset, outperforming frame-wise attacks and state-of-the-art query-based attacks. To interpret the mechanisms underlying these attacks, we introduce quantitative metrics based on Explainable AI (XAI) analysis. Spatial analysis reveals systematic disruption of attention patterns, with adversarial examples showing median SSIM scores of 0.353. Temporal correlation analysis also demonstrates severe degradation in attention coherence across frame sequences. Through experiments comparing previous attack methods, including common corruptions benchmark, frame-wise attacks, sparse attacks, and recent V-BAD attacks, we demonstrate that our proposed method is more effective in transformer-based video models. This study further examines the adversarial training strategy against the selected attacks. To promote reproducibility and facilitate future research, we provide our methods and analysis tools through a public GitHub repository. These findings underscore the effectiveness of jointly considering spatial and temporal dimensions when developing adversarial attack strategies and defense mechanisms for video AI models.
- Open Access
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 101647-101661
STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-Based AI Video Models
Transformer-based video models have performed SOTA in various action recognition and video understanding tasks. The limitation is the lack of explainability of these complex models. Current Explainable AI (XAI) methods focus on feature importance analysis of only one dimension, either spatial or temporal features. When applied to transformer-based video models, the challenges are two-fold. They fail to capture the integrated spatio-temporal nature of video data and incur prohibitive computational costs for real-time applications. This paper presents STAA (Spatio-Temporal Attention Attribution), an XAI method for interpreting video transformer models for action recognition tasks. STAA simultaneously extracts both spatial importance within frames and temporal relevance across the video sequence from attention values in transformers. This unified approach solves the challenge by capturing how transformer models integrate information across both dimensions for decision-making, providing comprehensive explanations that reflect the model’s actual reasoning process. We enhance STAA’s raw output through post-processing. The experiments on the Kinetics-400 dataset demonstrate superior faithfulness (0.844 ± 0.116) and monotonicity (0.850 ± 0.030). In terms of computational overhead, our STAA method is applicable for real-time video XAI analysis applications. We implement a cloud-based architecture that enables video explanations with 150 ms latency.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 101647-101661
Open AccessSTAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-Based AI Video Models
Transformer-based video models have performed SOTA in various action recognition and video understanding tasks. The limitation is the lack of explainability of these complex models. Current Explainable AI (XAI) methods focus on feature importance analysis of only one dimension, either spatial or temporal features. When applied to transformer-based video models, the challenges are two-fold. They fail to capture the integrated spatio-temporal nature of video data and incur prohibitive computational costs for real-time applications. This paper presents STAA (Spatio-Temporal Attention Attribution), an XAI method for interpreting video transformer models for action recognition tasks. STAA simultaneously extracts both spatial importance within frames and temporal relevance across the video sequence from attention values in transformers. This unified approach solves the challenge by capturing how transformer models integrate information across both dimensions for decision-making, providing comprehensive explanations that reflect the model’s actual reasoning process. We enhance STAA’s raw output through post-processing. The experiments on the Kinetics-400 dataset demonstrate superior faithfulness (0.844 ± 0.116) and monotonicity (0.850 ± 0.030). In terms of computational overhead, our STAA method is applicable for real-time video XAI analysis applications. We implement a cloud-based architecture that enables video explanations with 150 ms latency.
- Open Access
- 28 March 2025
- Published by Qeios Ltd
Review of: "Explaining the Unexplainable: A Systematic Review of Explainable AI in Finance"
This article offers a well-executed survey of XAI applications within the financial domain. The authors provide a wide-ranging overview of 323 peers. The study also acknowledges the trade-offs between interpretability and predictive power in financia...
- 28 March 2025
- Published by Qeios Ltd
Open AccessReview of: "Explaining the Unexplainable: A Systematic Review of Explainable AI in Finance"
This article offers a well-executed survey of XAI applications within the financial domain. The authors provide a wide-ranging overview of 323 peers. The study also acknowledges the trade-offs between interpretability and predictive power in financia...
- 10 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 12 (2) , 762-776
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
This paper presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services' trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.
- 10 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 12 (2) , 762-776
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
This paper presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services' trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 67-71
XAIport: A Service Framework for the Early Adoption of XAI in AI Model Development
In this study, we propose the early adoption of Explainable AI (XAI) with a focus on three properties: Quality of explanation, the explanation summaries should be consistent across multiple XAI methods; Architectural Compatibility, for effective integration in XAI, the architecture styles of both the XAI methods and the models to be explained must be compatible with the framework; Configurable operations, XAI explanations are operable, akin to machine learning operations. Thus, an explanation for AI models should be reproducible and tractable to be trustworthy. We present XAIport, a framework of XAI microservices encapsulated into Open APIs to deliver early explanations as observation for learning model quality assurance. XAIport enables configurable XAI operations along with machine learning development. We quantify the operational costs of incorporating XAI with three cloud computer vision services on Microsoft Azure Cognitive Services, Google Cloud Vertex AI, and Amazon Rekognition. Our findings show comparable operational costs between XAI and traditional machine learning, with XAIport significantly improving both cloud AI model performance and explanation stability.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 67-71
Open AccessXAIport: A Service Framework for the Early Adoption of XAI in AI Model Development
In this study, we propose the early adoption of Explainable AI (XAI) with a focus on three properties: Quality of explanation, the explanation summaries should be consistent across multiple XAI methods; Architectural Compatibility, for effective integration in XAI, the architecture styles of both the XAI methods and the models to be explained must be compatible with the framework; Configurable operations, XAI explanations are operable, akin to machine learning operations. Thus, an explanation for AI models should be reproducible and tractable to be trustworthy. We present XAIport, a framework of XAI microservices encapsulated into Open APIs to deliver early explanations as observation for learning model quality assurance. XAIport enables configurable XAI operations along with machine learning development. We quantify the operational costs of incorporating XAI with three cloud computer vision services on Microsoft Azure Cognitive Services, Google Cloud Vertex AI, and Amazon Rekognition. Our findings show comparable operational costs between XAI and traditional machine learning, with XAIport significantly improving both cloud AI model performance and explanation stability.
- Open Access
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
This paper presents the design of an open-API-based explainable AI (XAI) service to provide feature-contribution explanations for cloud AI services. Cloud AI services have broad usage in developing domain-specific applications with learning precision metrics. However, the underlying AI models remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud AI services. We can also utilize this architecture to evaluate the performance and XAI consistency metrics showing cloud AI services' trustworthiness. We collect provenance data from XAI operations to enable traceability within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding performance and XAI consistency metrics for the leading cloud AI services for computer vision. The results confirm the open-API-based architecture cloud-agnostic. Additionally, data augmentation has a marked improvement in XAI consistency metrics for the cloud AI services.
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessAn Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
This paper presents the design of an open-API-based explainable AI (XAI) service to provide feature-contribution explanations for cloud AI services. Cloud AI services have broad usage in developing domain-specific applications with learning precision metrics. However, the underlying AI models remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud AI services. We can also utilize this architecture to evaluate the performance and XAI consistency metrics showing cloud AI services' trustworthiness. We collect provenance data from XAI operations to enable traceability within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding performance and XAI consistency metrics for the leading cloud AI services for computer vision. The results confirm the open-API-based architecture cloud-agnostic. Additionally, data augmentation has a marked improvement in XAI consistency metrics for the cloud AI services.
- 10 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 56 (4) , 50-60
A Trustworthy View on Explainable Artificial Intelligence Method Evaluation
In this article, we follow a process of explainable artificial intelligence (XAI) method development and define two metrics in terms of consistency and efficiency in guiding the evaluation of XAI explanations.
- 10 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 56 (4) , 50-60
A Trustworthy View on Explainable Artificial Intelligence Method Evaluation
In this article, we follow a process of explainable artificial intelligence (XAI) method development and define two metrics in terms of consistency and efficiency in guiding the evaluation of XAI explanations.