Just as the aviation industry gained public trust by adopting rigorous safety protocols, AI companies must identify and address critical vulnerabilities before they cause real-world harm. — 123rf
IN A recent security test, a generative AI banking chatbot designed to assist customers with loan applications was manipulated into disclosing sensitive financial information. Testers bypassed security controls and extracted a comprehensive list of loan approvals, including customer names.
This cautionary tale underscores a fundamental issue: generative AI could revolutionise entire industries, but, without robust safety protocols, it can also lead to disastrous outcomes.
