News
Study tests if AI can help fight cybercrime
Artificial Intelligence (AI) could become a crucial asset to fight the growing global risk of cybercrime, a new study with Charles Darwin University (CDU) has found.
The study, led by researchers from CDU’s Energy and Resources Institute alongside Christ Academy Institute for Advanced Studies in India, examined if generative AI (GenAI) could be used in penetration testing, known as pentesting, which is a cybersecurity exercise aimed at identifying weak spots in a system’s defences.
Researchers used ChatGPT to run a series of pentesting activities in reconnaissance, scanning, vulnerability assessments, exploitation, and reporting activities.
Prompts included trying to anonymously log into a server and download files, inspect source codes of webpages, and find data embedded within an archive.
Co-author and CDU Senior Lecturer in Information Technology Dr Bharanidharan Shanmugam said the purpose of the study was to explore whether AI could be used to automate some pentesting activities, with the results showing ChatGPT had enormous potential.
“In the reconnaissance phase, ChatGPT can be used for gathering information about the target system, network, or organisation for the purpose of identifying potential vulnerabilities and attack vectors,” Dr Shanmugam said.
“In the scanning phase, ChatGPT can be used to aid in performing detailed scans of the target particularly their network, systems and applications to identify open ports, services, and potential vulnerabilities.
“While ChatGPT proved to be an excellent GenAI tool for pentesting for the previous phases, it shone the greatest in exploiting the vulnerabilities of the remote machine.”
Dr Shanmugam added while the technology could revolutionise pentesting, use of AI to improve cybersecurity must be strictly monitored.
“Organisations must adopt best practices and guidelines, focusing on responsible AI deployment, data security and privacy, and fostering collaboration and information sharing,” he said.
“By doing so, organisations can leverage the power of GenAI to better protect themselves against the ever-evolving threat landscape and maintain a secure digital environment for all.”
Generative AI for pentesting: the good, the bad, the ugly was published in the International Journal of Information Security.
Related Articles
‘Ecological engineers’ an existential threat to wildlife of iconic wetland
A study examining how feral water buffalo interact with landscapes has uncovered how the pest is having disastrous impacts on northern long-necked turtles in the Top End’s tropical wetlands.
Read more about ‘Ecological engineers’ an existential threat to wildlife of iconic wetland
Indigenous people want violence out of their communities. Here’s a new approach
Read more about Indigenous people want violence out of their communities. Here’s a new approachElders say there are many drivers of community violence and unrest that go unaddressed by typical law and order responses. Here’s what they’re doing instead.
How 9000 photos built the foundation for AI-driven crop disease detection
A breakthrough in AI-driven crop disease detection is set to reduce harvest losses and chemical-related health risks thanks to a first-of-its-kind tomato leaf dataset comprising almost 9000 images of tomato images.
Read more about How 9000 photos built the foundation for AI-driven crop disease detection
