Professor Jun Murai
Distinguished Professor, Keio University
Founder, WIDE Project
Internet Civilization
The Internet is more than just a network of computers; it represents a civilization born from the sciences of mathematics and physics and nurtured by human ingenuity. For the first time, the Internet has created a truly global space, profoundly impacting our society, economy, and way of life. A key feature of Internet Civilization is its speed, with light-speed latency of just 133 milliseconds between any two points on Earth. This has enabled new forms of communication and collaboration, such as real-time gaming across continents and remote surgeries.
Additionally, Internet Civilization leverages distributed computing, pooling the power of millions of devices worldwide. This capability has led to advancements of computing digital data in censoring and monitoring, also in artificial intelligence and machine learning.
The next frontier is the Interplanetary Network (IPN), which will connect Earth with other planets and moons in our solar system, creating a galactic civilization. At ICICT 2024, we will explore the challenges and opportunities of this new era and discuss technology architecture and also its societal, economic, and ethical implications.
Professor Latifur Khan
Fellow of IEEE, IET, BCS
Professor, Department of Computer Science, University of Texas at Dallas (UT Dallas), USA
Generative AI including Large Language Models for Social Good & Cyber-Security
In this presentation, I will explore three applications of generative AI, specifically Large Language Models (LLMs), in the domains of political conflicts, cyber-threat reports, and Federal and State legislations related to autonomous vehicles.
We’ve conducted global monitoring of conflicts and political violence by analyzing vast amounts of specialized text. Collaborating with a multidisciplinary team, we developed ConfliBERT, a domain-specific pre-trained language model focused on conflict and political violence in English. ConfliBERT is publicly available on Github and Hugging Face. Since its recent release, the models have been downloaded over 14,000 times from Hugging Face, indicating significant interest. During this talk, we will demonstrate how our model outperforms standard LLMs in various tasks such as classification and question answering.
In collaboration with researchers from NIST, we’ve focused on automating the extraction of attack techniques from Common Vulnerabilities and Exposures (CVE) and Cyber Threat Intelligence (CTI) reports. Subsequently, we map these techniques to the standardized MITRE ATT&CK framework using Large Language Models (LLMs) and active learning. During this talk, we will illustrate how this curated knowledge will be crucial in enabling security analysts to respond effectively to cyber threats.
Utilizing LLMs, including Retrieval-Augmented Generation (RAG), we’ve identified gaps in Federal and State legislation concerning data privacy and cybersecurity within the autonomous vehicle domain. In this presentation, we will demonstrate how additions or modifications to the existing legislative framework can address potential scenarios as they arise.
*This work is funded by NSF, DOT, NIH, ONR, ARMY, and NSA. The work, ConflictBERT is in collaboration with Dr. Patrick Brandt, and Dr. Jennifer Holmes, (School of Economic, Political and Policy Sciences, UT Dallas).
Md. Altaf-Ul-Amin
Associate Professor, NAIST, Japan
Computational Approaches to Predict Natural Antibiotics based on Traditional Herbal Medicines
Antibiotic resistance is a major public health threat and there is an urgent need for new antibiotics. Traditional herbal medicine systems, such as Jamu, Unani, and Traditional Chinese Medicine, have been used for centuries to treat bacterial infections. Machine learning methods have been shown to be effective for predicting potential natural antibiotic candidates based on traditional herbal medicine systems. In this study, we used machine learning methods to predict potential natural antibiotic candidates at plant and metabolite levels. We evaluated different machine learning algorithms and preprocessing techniques to obtain the best prediction accuracy. For Jamu, we achieved an accuracy of 91.10% using the Random Forest model. For Unani, we achieved an accuracy of 83% using a multilayer perceptron model with SMOTE preprocessing. In total, we predicted 42 potential plant candidates and 201 candidate metabolites as potential natural antibiotics. Many of these candidates have been validated based on published literature mentioning their antibacterial properties. Some others are structurally similar to known antibiotics. Our findings suggest that machine learning methods can be used to effectively predict potential natural antibiotic candidates utilizing traditional herbal medicines. This approach has the potential to accelerate the development of new antibiotics to combat antibiotic-resistant pathogens.
Prof. Dr. Ishak Aris
Professor, Dept. of Electrical and Electronic Engineering, Faculty of Engineering, University Putra Malaysia
Current Trends and Future Prospects of Electric Vehicle Communication System
Recently, the Electric Vehicles (EV) market is experiencing significant growth and development worldwide. In 2024, the revenue in the EV market is projected to reach a staggering US$623.3bn worldwide. Looking ahead, it is expected that the market will demonstrate a steady annual growth rate (CAGR 2024-2028) of 9.82%. With the new requirements of the electric vehicles, a vehicle communication system is an important system component in a vehicle architecture. Among its functions include providing communication link between a driver and vehicle, a supervisory controller and sub-system controllers, vehicle-to-vehicle, vehicle-to-infrastructure and vehicle-to-everything. The concepts of intelligent energy efficient electric vehicle that require a new approach of vehicle communication system will be discussed. It will also include discussion on the implementation of optical fiber in vehicle communication architecture which can offer very high speed data communication with multi-channel features. Collaboration projects with local car manufacturer will also be highlighted.