Eoin Wickens, Director of Threat Intelligence at HiddenLayer, is a leading expert in AI security and threat research. In this insightful discussion, Eoin tackles the evolution of AI vulnerabilities, emphasizing the risks of shadow AI and model poisoning. He sheds light on the rising threat of deep fakes in communications, raising alarm bells over trust and authenticity. The importance of structured testing frameworks for securing AI is highlighted, alongside the ethical concerns surrounding adversarial machine learning and the need for new security paradigms in the rapidly changing AI landscape.
