Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (Cyborg)
  • No Skin
Collapse
Brand Logo

CIRCLE WITH A DOT

  1. Home
  2. Uncategorized
  3. @adamshostack how is your experience with using LLMs or agentic AI for threat modeling?

@adamshostack how is your experience with using LLMs or agentic AI for threat modeling?

Scheduled Pinned Locked Moved Uncategorized
5 Posts 2 Posters 0 Views
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • d3tm4r@infosec.exchangeD This user is from outside of this forum
    d3tm4r@infosec.exchangeD This user is from outside of this forum
    d3tm4r@infosec.exchange
    wrote last edited by
    #1

    @adamshostack how is your experience with using LLMs or agentic AI for threat modeling? I have so far tried GPT5 for creating attack trees and to find STRIDE threats from a textual prompt describing the goal, setup, elements etc. The results were good enough to use as a starting point for further refinement. What I'm wondering now is, if I could achieve similar results using a self hosted, smaller ai model and feed it a well structured draw.io diagram of the environment containing the elements, data flows and trust boundaries instead of a free textual prompt. Has anyone done this before or are you aware of any ready to go tools for self-hosting that can do that? I don't want to feed public LLMs any information about what threat models I want to create.

    adamshostack@infosec.exchangeA 1 Reply Last reply
    0
    • d3tm4r@infosec.exchangeD d3tm4r@infosec.exchange

      @adamshostack how is your experience with using LLMs or agentic AI for threat modeling? I have so far tried GPT5 for creating attack trees and to find STRIDE threats from a textual prompt describing the goal, setup, elements etc. The results were good enough to use as a starting point for further refinement. What I'm wondering now is, if I could achieve similar results using a self hosted, smaller ai model and feed it a well structured draw.io diagram of the environment containing the elements, data flows and trust boundaries instead of a free textual prompt. Has anyone done this before or are you aware of any ready to go tools for self-hosting that can do that? I don't want to feed public LLMs any information about what threat models I want to create.

      adamshostack@infosec.exchangeA This user is from outside of this forum
      adamshostack@infosec.exchangeA This user is from outside of this forum
      adamshostack@infosec.exchange
      wrote last edited by
      #2

      @d3tm4r I've blogged on this extensively, for example https://shostack.org/blog/lessons-from-owasp/ (and dig through the AI category) I haven't dug at all into the local/frontier model tradeoffs.

      d3tm4r@infosec.exchangeD 1 Reply Last reply
      0
      • adamshostack@infosec.exchangeA adamshostack@infosec.exchange

        @d3tm4r I've blogged on this extensively, for example https://shostack.org/blog/lessons-from-owasp/ (and dig through the AI category) I haven't dug at all into the local/frontier model tradeoffs.

        d3tm4r@infosec.exchangeD This user is from outside of this forum
        d3tm4r@infosec.exchangeD This user is from outside of this forum
        d3tm4r@infosec.exchange
        wrote last edited by
        #3

        @adamshostack I have read some of your blog articles on the topic. Thanks for pointing me to them. I see now that despite my general skepticism I was still too enthusiastic about the first results that I got out of ChatGPT.
        I am teaching threat modeling for beginners for a few years now and established threat modeling in our organization's quality gates but still adoption is far below what I think is needed. So I was hoping to make it easier for people by means of automation and since LLMs are the rage it is worth a try. But results have to be of consistent quality and quantity even if they should be regarded as a starting point only.
        To be honest, I'd prefer deterministic tools that can leverage threat libraries and frameworks and take a DFD or architecture diagram as input. However I haven't found any good tools for self hosting so far. The time that I have for this is very limited though since my main job is being a SOC manager nowadays.

        1 Reply Last reply
        0
        • d3tm4r@infosec.exchangeD This user is from outside of this forum
          d3tm4r@infosec.exchangeD This user is from outside of this forum
          d3tm4r@infosec.exchange
          wrote last edited by
          #4

          @adamshostack @tychotithonus a new day, a new shot at using ChatGPT for threat modeling.
          It did a pretty decent job identifying elements, data flows and trust boundaries from my draw.io DFD but it listed very few threats in the beginning.
          I then promoted it to find more threats, focus on the element that has to be protected and use threats from the Microsoft EoP card game, which resulted in some more threats. Have to review the results more thoroughly later though.
          Here's a gist: https://gist.github.com/test4bounty/7d78a5fca56645db6ca2e3d7193525a5

          d3tm4r@infosec.exchangeD 1 Reply Last reply
          1
          0
          • R relay@relay.infosec.exchange shared this topic
          • d3tm4r@infosec.exchangeD d3tm4r@infosec.exchange

            @adamshostack @tychotithonus a new day, a new shot at using ChatGPT for threat modeling.
            It did a pretty decent job identifying elements, data flows and trust boundaries from my draw.io DFD but it listed very few threats in the beginning.
            I then promoted it to find more threats, focus on the element that has to be protected and use threats from the Microsoft EoP card game, which resulted in some more threats. Have to review the results more thoroughly later though.
            Here's a gist: https://gist.github.com/test4bounty/7d78a5fca56645db6ca2e3d7193525a5

            d3tm4r@infosec.exchangeD This user is from outside of this forum
            d3tm4r@infosec.exchangeD This user is from outside of this forum
            d3tm4r@infosec.exchange
            wrote last edited by
            #5

            @adamshostack @tychotithonus doesn't look like threats from the EoP card game were in the training data. 😉

            1 Reply Last reply
            1
            0
            Reply
            • Reply as topic
            Log in to reply
            • Oldest to Newest
            • Newest to Oldest
            • Most Votes


            • Login

            • Login or register to search.
            • First post
              Last post
            0
            • Categories
            • Recent
            • Tags
            • Popular
            • World
            • Users
            • Groups