Workshop 1: Artificial Intelligence in Signal Processing and Pattern Recognition

This workshop aims to create a dynamic platform that fosters collaboration and knowledge exchange among a diverse community of researchers, practitioners, and industry experts. By gathering experts from various disciplines, including signal processing, pattern recognition, and artificial intelligence (AI), we seek to facilitate insightful discussions on the latest advancements, emerging challenges, and untapped opportunities in the exciting field of AI applied to signal processing and pattern recognition. During the workshop, participants will have the opportunity to delve into cutting-edge research and explore the intersection of AI algorithms, methodologies, and techniques with signal processing and pattern recognition domains. By sharing their experiences, novel methodologies, and experimental results, attendees will collectively contribute to a deeper understanding of the potential of AI in addressing real-world problems. Furthermore, the workshop aims to foster interdisciplinary collaborations, bridging the gap between theoretical advancements and practical applications, thereby accelerating the adoption of AI techniques in signal processing and pattern recognition across various industries.

•Machine learning and deep learning techniques for signal processing and pattern recognition 
•AI-based approaches for image and video analysis, speech and audio processing, and natural language processing 
•Intelligent signal processing algorithms and methodologies for data representation, feature extraction, and dimensionality reduction 
•AI-driven techniques for pattern recognition in various domains, such as biometrics, healthcare, finance, and cybersecurity 
•Applications of AI in signal processing and pattern recognition, including object recognition, anomaly detection, and signal classification


Yudong Zhang
University of Leicester, UK

Shuwen Chen
Jiangsu Second Normal University, China

Xiaoyan Zhao
Nanjing Institute of Technology, China

Workshop 2: Emerging Complex Network Control Systems Using Computational Intelligence

Nowadays, complex network control systems (NCSs), such as smart grid, big data, cloud control system and teleoperation system, serve as a primary concern in real time operation of various industrial systems, posing great challenges on behavioral patterns under abnormal conditions. Thus, NCSs possess the new characteristics of wide areas, wide ranges, large data, etc., which play a significant role in identifying abnormal patterns of industrial system behaviors under highly loaded scenarios such as delay and packet dropouts. Lately, plenty of NCS tools have been built, however some doubts were raised about the efficiency of those tools due to lack of explainable schemes to process numerous uncertain evaluation data. Thus, exploring emerging NCS techniques is imperative.  

Computational Intelligence (CI) mainly involves the theory, design, application and development of biologically and linguistically motivated computational paradigms. In general, three main pillars of CI are neural networks, fuzzy systems and evolutionary computation. With the rapid growth of big data era and cloud computing, the role of CI in control has emerged. Specifically, it focuses on four topics within the CI area: neural network control, fuzzy control, reinforcement learning and brain machine interfaces. Additional topics, such as knowledge-based systems, evolutionary algorithms and swarm intelligence systems are also included in the extensive studies of CI in control. Inspired by the merits of CI in control, individuals are able to develop explainable intelligent tools for NCSs and eventually completing the task of designing valid NCSs. Therefore, exploring emerging NCSs by virtue of CI in control is likely to provide an efficient way for constructing state-of-the-art NCSs. 

The aim of this workshop is to bring together original research review articles discussing emerging NCSs using CI. 

  • Potential topics include but are not limited to the following: 
  • Neural network control for complex network control systems; 
  • Fuzzy theories and applications for complex network control systems; 
  • Reinforcement learning in feedback control systems; 
  • Network security applications via complex network control systems; 
  • Brain machine interfaces for complex network control systems; 
  • Predictive control method for network control systems; 
  • Social reasoning used in novel network control analysis; 
  • Knowledge-based systems for complex network control systems; 
  • Evolutionary algorithms for complex network control systems; 
  • Swarm intelligence for complex network control systems; 
  • Granular Computing for complex networks under uncertainties; 
  • Other emerging computational intelligence techniques for network control systems.

Computational intelligence; Network control systems; Granular computing


Wentao Li
Southwest University, China

Chao Zhang
Shanxi University, China

Huiyan Zhang
Chongqing Technology and Business University, China

Tao Zhan
Southwest University, China

Workshop 3: Deep Learning in Medical Imaging- Disease Segmentation and Classification

Deep learning showed a huge interest in the area of computer vision in the last few years, especially for the application of medical imaging. In medical imaging, deep learning is employed for the detection and classification of cancers such as skin cancer, stomach cancer, brain tumor, and a few more. For these cancers, dermoscopy, wireless capsule endoscopy, and MRI imaging technologies are adopted. For a computerized technique, preprocessing, segmentation, feature extraction, selection, and classification steps are employed. The contrast enhancement using deep learning techniques is useful when a fully automated system is designed. In addition, lesion segmentation is performed using custom CNN models, U-NET, and deep saliency maps. For feature extraction, deep learning based features are extracted. For this several pre-trained models, GAN, residual networks, and LSTM models are adopted. Recently, federated learning is showing much success in the classification process in medical imaging. Furthermore, the features fusion and selection process improve the performance of the proposed framework and reduced the testing time.

Skin cancer, Explainable AI, GradCAM, LIME, Residual blocks, fusion using CCA, optimization, classification


Muhammad Attique Khan 
Department of CS, HITEC University, Taxila, Pakistan

Yu-dong Zhang 
Department of Informatics, University of Leicester, UK

Tallha Akram
Department of ECE, COMSATS University Islamabad, Pakistan

Zhewei Liang
Advanced Diagnostics Laboratory (ADL), Quantitative Health Sciences (QHS), Mayo Clinic, USA

Workshop 4: Artificial Intelligence for Security

With the rapid development of deep learning technology, artificial intelligence (AI) has emerged as a popular area of research in the field of security, which provides us with significant applications for safeguarding and managing risks. Through intelligent threat detection and prevention techniques, it discerns the signs of malicious behavior, guarding the security boundaries of our networks. With anomaly detection and identity verification, it captures unusual activities and ensures the legitimacy of access. In data protection and privacy, it employs encryption and anonymization to shield sensitive information with utmost care. Additionally, leveraging video surveillance and image recognition technologies, it enables us to swiftly perceive anomalies and real-time behaviors, safeguarding the realm of security. Overall, the ability of AI for automated security response empowers us to swiftly address security incidents, as well as enhances response efficiency, bringing serenity and harmony to our digital world. However, the performance of AI models still needs to be improved, which is not yet at the same level as humans in several fields, such as lacking explainability in deep learning models, susceptibility to adversarial attacks, potential biases in training data, limitations in generalization, and ethical considerations. Moreover, the limited generalization abilities of AI models and ethical concerns surrounding privacy infringement and surveillance further highlight the need for improvement. Furthermore, the concealed security risks inherent in AI systems should not be disregarded. For instance, attackers can inject slight noise into voice commands to smart home devices, causing them to execute malicious applications. The fundamental reason behind these security risks lies in the lack of consideration for relevant threats during the initial design of AI algorithms, making them susceptible to manipulation by malicious actors and resulting in inaccurate judgments by AI systems. In critical domains such as industry, healthcare, transportation, and surveillance, the consequences of such security hazards can be significant, ranging from property damage to potential threats to personal safety. This special issue aims at exploring the implications of AI for security in various industries and applications. We welcome submissions that examine the technical challenges and opportunities of AI for security, as well as the ethical and legal implications of using this technology. We also encourage submissions that explore the potential of AI for improving accuracy and generalization in AI models. 

Scope: This special issue seeks original contributions from, but not limited to, the following topics: 
AI data privacy protection 
AI approaches for adversarial attack detection 
Technical advances of AI in threat detection and prevention 
AI for identity authentication. 
Data-driven security innovation 
Secure multiparty computation 
Secret information embedding 
Human behavior models with application to security 
AI for security software verification and validation 
Automation of heterogeneous security tools 
Security and privacy 
Digital steganography 
Abnormal/Intrusion behavior detection and tracking. 
Vulnerability detection 
Security data fusion across multiple data sources 
Prevention of AI algorithm details leakage 
Data de-identification, differential privacy and secure multiparty computation 
Event correlation and anomaly detection 
Backdoor attack detection 
Bypass attack detection 
Poisoning attack prevention 
Watermark removal detection 
Model inversion prevention 
Model reprogramming attack detection

Artificial Intelligence, Deep Learning Algorithm, Security, Attacking, Prevention


Yi Ding
University of Electronic Science and Technology of China (UESTC), China

Xianhua Niu
Xihua University, China

Yingjie Zhou
Sichuan University (SCU), China

Dajiang Chen
University of Electronic Science and Technology of China (UESTC)

Workshop 5 Artificial Intelligence for Edge Computing

Edge Computing is a new computing paradigm where server resources, ranging from a credit-card size computer to a small data center, are placed closer to data and information generation sources. Application and systems developers use these resources to enable a new class of latency and bandwidth sensitive applications that are not realizable with current cloud computing architectures. Edge computing represents a counterpoint to the consolidation of computing into massive data centers, which has dominated the discourse in cloud computing for well over a decade. Popular terms such as micro-data centers, intelligent edges, cloudlets, and fog have been used interchangeably to describe edge computing. 

Artificial intelligence techniques can be applied in the edge computing to develop some various smart systems it includes smart city and smart home, smart grid, smart industry, smart vehicle, smart health, and smart environmental monitoring. New AI and ML real time or execution time algorithms are needed, as well as different strategies to embed these algorithms in edges. New clustering and classification techniques, reinforcement learning methods, or data quality approaches are required, as well as distributed AI algorithms. 

The aim of this workshop is to offer a forum for exchanging and proposing new ideas and techniques related with the design and usage of artificial intelligence techniques in edge computing. More specifically, we invite recent advanced research on artificial intelligence techniques privacy enhancing technologies and secure cryptographic techniques to address performance and security challenges in the field of edge computing.

Artificial Intelligence, Edge Computing

Fang Liu
Hunan University, China
Zhiping Cai
National University of Defense Technology, China

Zongshuai Zhang
Chinese Academy of Sciences, China

  • Daniel Xiapu Luo, The Hong Kong Polytechnic University, Hong Kong, China

Workshop 6 Cyber Security with Big Data

Cyberspace and its underlying infrastructure are vulnerable to a wide range of risk stemming from both physical and cyber threats and hazards. In light of the risk and severe consequences of cyber events, strengthening the security and resilience of cyberspace has become an important security mission. Moreover, the advent of big data provides a more powerful and intelligent way of defending against the risk in cyberspace than ever before. Hence, the Workshop on Cyber Security with Big Data(CSBD) aims to provide a forum for researchers and practitioners from academia and industry to exchange their latest research findings, novel ideas, and valuable comments regarding cyber security with big data. Its major concerns include cyber security theories, system design and implementation for cyber security, big data service for cyber security, artificial intelligence security, blockchain service for cyber security and emerging cyber security applications. The workshop program will consist of oral presentation sessions, where each presenter will show his/her work followed by Q/A, and an open discussion session.

Cyber Security, Big Data, Artificial Intelligence, Blockchain


Jieren Cheng
Hainan University, China

Xinwang Liu
National University of Defense Technology, China

Qiang Liu
National University of Defense Technology, China

Xiangyang (Alex X.) Liu
Michigan State University, USA

Workshop 7 Big Data and Big Model Applications

The application of big data and big models has become an important trend in many fields, including business, science, healthcare, and engineering. This workshop acts as a major forum for the presentation of innovative ideas, approaches, developments, and research projects in the areas of Big Data and Big Model Applications. It will also serve to facilitate the exchange of information between researchers and industry professionals to discuss the latest issues and advancement in the area of and Big Model Applications. Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in Big Data and Big Model Applications.

Scope and Topics: 
• Big Data Techniques, Models and Algorithms 
• Big Data Infrastructure and Platform 
• Big Data Search and Mining 
• Bioinformatics Big Data Security, Privacy and Trust 
• Big Data Applications, Multimedia etc 
• Big Data Tools and Systems 
• Big Data Mining 
• Big Data Management 
• Cloud and Grid Computing for Big Data 
• Machine Learning and AI for Big Data 
• Big Data Analytics and Social Media 
• 5G and Networks for Big Data 
• Big Data Applications in Education, Healthcare... etc.

Big Data, Big Model, Big Data Algorithms, AI


Wei Fang
Nanjing University of Information Science & Technology, China

Victor S. Sheng
Texas Tech University, USA

Program Committee: 
Victor S. Sheng,Texas Tech University, USA 
Wei Fang, Nanjing University of Information Science & Technology, China 
Naixue Xiong, Northeastern State University, USA 
Xiaoyong Yuan, University of Florida, USA 
Weiting Chen, East China Normal University, China 
XueJuan Liu, Southeast University, China 
Qi Wang, Nanjing University of Information Science and Technology, China 
Jun Li, Nanjing University of Science and Technology, China 
Shukui Zhang, Soochow University, China 
Maofu Liu, Wuhan University of Science and Technology,China 
Shubi Wang, Jiangsu University, China 
Yanyan Zheng, Lishui University, China 
Xuefeng Xian, Suzhou Vocational University, China

Workshop 8 Artificial Intelligence and Multimedia Security

The Workshop on Artificial Intelligence and Multimedia Security serves as a prominent platform for researchers to explore the critical area of ensuring the security of artificial intelligence models, particularly in the context of multimedia data. 

In recent years, the integration of artificial intelligence and multimedia has become an essential research focus, attracting significant attention from government, academia, and industry worldwide. The workshop aims to highlight the importance of addressing security challenges associated with artificial intelligence models, emphasizing the specific vulnerabilities and threats posed by multimedia data. Multimedia plays a vital role in various applications, such as image recognition, video analysis, and audio processing, making its security paramount for the overall integrity and reliability of AI systems. 

This workshop will bring together workshop organizers, platform providers, and participants to discuss the latest research topics in the field of artificial intelligence and multimedia security, with the aim of advancing the field of AI and multimedia security.

Scope and Topics: 
Deep Neural Networks with Watermarking 
Deep Learning for Multimedia Multimedia analysis for forensics 
Formal methods of computer and network forensic 
Steganography and steganalysis 
Watermarking and detection 
Digital forensics surveillance technology and procedure 
Software recognition and reverse analysis 
IP geolocation 
Security protocols and protocol analysis 
Network attack source tracing technologies 
Network covert channel detection
CAPTCHA recognition

Deep Learning; Deep Neural Networks; Multimedia analysis for forensics; Steganography and steganalysis; Watermarking and detection


Jinwei Wang
Nanjing University of Information Science and Technology, China

Leiming Yan
Nanjing University of Information Science and Technology

Program Committee:
Qingfeng Cheng, Zhengzhou Science and Technology Institute, China 
Shichang Ding, University of Gottingen, Germany 
Yanqing Guo, Dalian University of Technology, China 
Zhenyu Li, University of York, UK 
Chuan Qin, University of Shanghai for Science and Technology, China 
Guangjie Liu, Nanjing University of Science and Technology, China 
Tong Qiao, Hangzhou Dianzi University, China 
Bo Wang, Dalian University of Technology, China 
Shijun Xiang, Jinan University, China

Workshop 9 Energy-efficient and Secure Computing for Artificial Intelligence and Internet of Things

In recent years, Artificial Intelligence (AI) has become a key component for building smart Internet-of-Things (IoT) and network infrastructures. With the development of AI computing algorithms and methods, nowadays, AI computing has evolved as a computational-hungry and data-hungry process. This has caused substantial electricity consumption with a large amount of financial and environmental costs (e.g., greenhouse gas emission). From a larger perspective, the global data centers had consumed 3% of global electricity consumption, ranking 11th in the list of country electricity consumption. It is necessary to reduce carbon emission over the next decade to deter escalating rates of the natural disaster. There are two aspects that we would like to pay attention to in this special issue. First, we welcome research on work to reduce the energy consumption of AI computing such as DNN training and inference on intelligent cloud, IoT computing and networking systems. Second, we want to explore this issue from an adversarial perspective. Specifically, we want to investigate the possibility of manipulating the AI computing services to cause more financial loss or environmental damage, as well as the corresponding countermeasures. Also, other energy efficient and secure AI computing methodologies and techniques are within the scope of this workshop.

Novel Energy-efficient Techniques in Intelligent IoT Systems 
Ultra Energy-aware Computing Techniques in Resource-constrained IoT devices 
Energy-oriented Attacks and Defenses in Smart IoT Computing Systems 
Training and Inference Timing Attacks and Defenses in AI-enabled IoT Computing Systems 
Latency-oriented Attacks and Defenses in AI-enabled IoT Networking Systems
Energy-efficient Resource Management for AI-enabled IoT Computing Systems 
Green Edge Computing and Edge Learning 
Hardware-level Energy-efficient Designs and Implementations 
Energy-efficient Coordination and Resource Allocation for Large-scale AI Computing Systems 
System-level Simulation, Prototyping, and Field-tests for AI-enabled Edge Devices 
Energy-efficient and Secure Federated Learning Techniques 
Cyber Security, Data Privacy, and Integrity in Green AI Computing systems
Novel Security Issues in Intelligent Cloud-edge Ecosystems


Jian Su
Nanjing University of Information Science and Technology, China

Zheng-guo Sheng
University of Sussex, UK

Si-guang Chen
Nanjing University of Posts and Telecommunications, China

Program Committee:
Shiguo Wang, Xiangtan University, China
Liang-bo Xie, Chongqing University of Posts and Telecommunications, China
Zi-long Jin, Nanjing University of Information Science and Technology, China
Wei Zhuang, Nanjing University of Information Science and Technology, China
Shu Fu, Chongqing University, China
Yue-yue Li, University of Electronic Science and Technology of China, China
Wei Wei, Xi'an University of Technology, China
Ya-dang Chen, Nanjing University of Information Science and Technology, China
Le Sun, Nanjing University of Information Science and Technology, China
Xiao-liang Wang, Hunan University of Science and Technology, China
Han-guang Luo, University of Electronic Science and Technology of China, China

Workshop 10 Data and System Security for AIoT

Artificial Intelligence of Things (AIoT) is a new paradigm that leverages artificial intelligence (AI) techniques to enhance the capabilities and functionalities of Internet of Things (IoT) systems. However, AIoT also faces various challenges and risks in terms of data and system security, such as data integrity, confidentiality, and availability, system robustness, reliability, and resilience, and security threats from malicious attackers and adversaries. Therefore, it is imperative to develop and deploy effective data and system security mechanisms and solutions for AIoT systems. This workshop invites researchers and practitioners to share their latest research findings, novel ideas, and practical experiences on data and system security issues and solutions for AIoT systems. The workshop will cover topics such as data encryption, compression, protection, privacy preservation, quality assessment, provenance, traceability, system design, architecture, testing, verification, fault tolerance, resilience, attack detection, prevention, analysis, response, security standards and protocols. 

This workshop covers all aspects of data and system security for AIoT systems, including but not limited to: 
Data encryption, compression, and protection for AIoT systems Data privacy preservation and anonymization for AIoT systems Data quality assessment and assurance for AIoT systems Data provenance and traceability for AIoT systems System design and architecture for secure AIoT systems System testing and verification for secure AIoT systems System fault tolerance and resilience for secure AIoT systems System attack detection and prevention for secure AIoT systems System attack analysis and response for secure AIoT systems System security standards and protocols for secure AIoT systems

AIoT, data security, system security, IoT security, artificial intelligence


Yanchao Zhao
Nanjing University of Aeronautics and Astronautics, China

Hao Han
Nanjing University of Aeronautics and Astronautics, China

Workshop 11 Zeroshot Learning without Data Input

Zeroshot Learning is an actively researched field of artificial intelligence. Generally considered as a significant step towards Artificial General Intelligence (AGI), zeroshot learning usually requires data input and is formulated as pretrained model learning or transfer learning. As deep neural network models becoming more and more complex, it is necessary to dwell upon a new paradigm in which zeroshot learning requires no data input excluding pretrained models or transfer learning because they require data input from other domains. Data agnostic models are much more necessary in the manufacturing industry where data are rare and sparse, and also, they should be more accurate than heuristics.

In this workshop, we would like to invite authors to submit papers based on the following topics :

  • Zeroshot Learning for Recommender Systems without Data Input
  • Zeroshot Learning for Natural Language Processing Tasks without Data Input
  • Zeroshot Learning for Computer Vision Tasks without Data Input
  • Zeroshot Learning in Medicine Industry without Data Input
  • Zeroshot Learning in Smart Industry without Data Input
  • Interpretability and Mathematical Foundation for Zeroshot Learning without Data Input
  • Zeroshot Learning in Social Science Studies

Zeroshot Learning, Artificial General Intelligence, Data-agnostic Model


Hao Wang
CEO & Founder of Ratidar Technologies LLC., China