The company acquired security intelligence tool Mandiant last year, providing valuable data about security threats to its customers. The new Duet AI tools help in summarizing this data, identifying threats, and recommending actions. However, the effectiveness of these tools will depend on the quality of the summaries and recommendations provided. Google is also addressing the "hallucination problem" of AI, where large language models make up things when they don't have a clear answer, by providing a more limited data set based on the information from these security tools. The three Duet AI products are currently in preview and will be released later this year.
Key takeaways:
- Google Cloud Next announced several new generative AI enhancements to its security product line, aiming to make it easier to find information from a massive amount of security data by simply asking questions in plain language.
- The company is introducing Duet AI in Mandiant Threat Intelligence, Chronicle Security Operations, and Security Command Center, which helps security teams understand the mass of information they are seeing by providing a relevant summary to help quickly grasp the nature of a particular threat.
- The usefulness of these AI tools could depend on the quality of the summary and recommendations that the model gives back, and how well less skilled analysts can understand the information they are getting.
- The hallucination problem, where large language models make up things when they don’t have a clear answer, could be a huge issue when it comes security. However, Google believes that providing a more limited data set, based on the information these security tools, could help mitigate that problem.