Keep your code secure from vulnerabilities by staying vigilant

TLDR:

• Cybercrime is on the rise with estimated damages of US$10.5 trillion annually by 2025.
• A research project led by SMU aims to develop an AI-powered model to identify vulnerabilities in government software.

Our embrace of digital technology has led to a surge in cybercrimes, with damages estimated to reach US$10.5 trillion annually by 2025. To address this pressing issue, Professor David Lo at Singapore Management University (SMU) is leading a research project to develop an AI-powered model to identify vulnerabilities in the source code of government software. The project aims to help agencies like the Government Technology Agency (GovTech) of Singapore’s Cyber Security Group (CSG) in securing digital government services. This initiative, supported by a TRANS grant, focuses on leveraging generative artificial intelligence algorithms to train a large language model specific for vulnerability discovery. By creating a data pipeline to continuously provide vulnerability data, the project intends to enhance cybersecurity practices and safeguard digital infrastructure. The research not only strives to improve government software security but also has the potential to influence global cybersecurity practices, emphasizing the importance of ongoing innovation and vigilance in the face of evolving cyber threats.