Technical Meeting on the Application of Artificial Intelligence for Nuclear Security

Contribution List

8. Deep Learning-Based Approach for Real-Time Radioisotope Identification: A Novel 1D CNN Model and Experimental Validation

Real-time radioisotope identification (RID) is an indispensable application in many critical areas, from environmental monitoring to national nuclear security. However, challenges posed by field conditions, such as the limited energy resolution of commonly used scintillation detectors like NaI(Tl), low counts, natural background radiation, and shielding, adversely affect the automatic...

7. Enhancing Industrial Control System Cybersecurity Using Artificial Intelligence for Critical Infrastructure: A Case Study on Modbus TCP Attack Detection

As Industrial Control Systems (ICS) continue to digitize and integrate with broader networks, cybersecurity threats targeting communication protocols have become a critical concern. Among these protocols, Modbus TCP—widely used in Supervisory Control and Data Acquisition (SCADA) systems. Artificial Intelligence (AI) offers a promising solution to enhance intrusion detection by learning complex...

12. Enhancing Nuclear Security Against AI Threats Through an Efficient Digital Forgery Detection Scheme

Hani Mahmoud (Nuclear Research Center, Atomic Energy Authority, Egypt)

Digital threats such as deepfakes and digital forgery have become significant challenges due to the rapid advancements in Artificial Intelligence (AI). This is particularly in the vital sectors like nuclear security where sensitive data, images, and documents are involved. The manipulation of digital content poses risks to the integrity of nuclear operations and inspections. This objective of...

9. Implementation of the Nuclear Forensic Assessment Software for Nuclear Threat Detection and Material Out of Regulatory Control

Ms Harinate Mungpayaban (Office of Atoms for Peace)

Nuclear Forensic Assessment Software is developed to bolster nuclear threat detection and material control. The Nuclear Forensic Assessment Software aims to link objects collected from crime scenes to nuclear and other radioactive material signatures for further investigation. As a result, authorities can obtain more information about nuclear and radioactive materials to manage the crime scene...

1. Leveraging Artificial Intelligence for Insider Threat Detection in Radiological Facilities in Ghana

Raymond Agalga (GHANA ATOMIC ENERGY COMMISSION)

Insider threats pose significant risks to radiological facilities, particularly in regions like Ghana where digital monitoring systems and advanced threat detection infrastructure are still evolving. Traditional security measures often struggle to detect sophisticated insider activities, which may involve authorized personnel exploiting legitimate access for malicious or negligent purposes....

10. Preliminary Development of an AI-UGV Integrated System for Radiological Object Inspection in Nuclear Security Applications

The integration of Artificial Intelligence (AI) with Uncrewed Ground Vehicle (UGV) presents a promising approach to enhance radiation detection capabilities. This paper presents preliminary work conducted under the Coordinated Research Project (CRP) J02018, “Nuclear Security Implications of Uncrewed Aerial, Ground, and Maritime Systems.” The Malaysian project aims to develop a proof-of-concept...