Summary
Ollie Whitehouse, NCSC Chief Technology Officer, said: “Recent incidents of frontier AI models carrying out unsanctioned actions and, in some cases, human-like deceptive behaviour on the open internet are a serious reminder of the risks AI capabilities pose. “These technologies must be developed and used from the outset with strong safeguards, real-time oversight, and clear plans for responding when the unexpected happens. Relying on detection alone after the fact of an incident will not be "As AI continues to evolve and create both opportunities and challenges, following established evidenced cyber security fundamentals, as set out by the NCSC’s guidance, remains essential to maintaining trust, resilience, and a defensive Guidelines for secure AI system development Thinking carefully before adopting agentic AI Frontier AI cyber security guidance & risks