ATHI — An AI Threat Modeling Framework for Policymakers

rw-book-cover
URL: https://danielmiessler.com/p/athi-an-ai-threat-modeling-framework-for-policymakers?utm_source=danielmiessler.com&utm_medium=newsletter&utm_campaign=unsupervised-learning-no-395

So when you hear someone say, “AI is really scary!”, try to steer them towards this type of thinking. Who would do that? How would they do it? What would happen as a result? And what would the be the effects of that happening? (View Highlight)

Note:: Great threat modeling questions.

Summary

  1. AI threats are both new and considerable, so it’s hard to think about them clearly.
  2. Threat Modeling has been used to do this for other security arenas for decades, and we should use something similar for AI.
  3. We can use a similar approach for AI, using something simple like ATHI.
  4. Hopefully the ability to have clear conversations about the problems will help us create better solutions. (View Highlight)