Get the latest tech news
Google Cloud’s security chief warns: Cyber defenses must evolve to counter AI abuses
How conventional cyber detection and response can be expanded to monitor for AI abuses — and how AI can be used for defensive advantage.
Venables pointed out that there are plenty of examples of people manipulating prompts both directly and indirectly to cause unintended outcomes in the face of “naively defended, or flat-out unprotected models.” End-to-end platforms can control the data and the software lifecycle and help manage the operational risk of AI integration into business and mission-critical processes and applications. It’s about filtering inputs and outputs to and from those models, then finally making sure you’re sandboxing more use and applications in some risk and control framework that provides defense in depth.”
Or read this on Venture Beat