Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • 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 (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. Other Discussions
  3. The Insider News
  4. Researchers hid malware inside an AI's 'neurons' and it worked scarily well

Researchers hid malware inside an AI's 'neurons' and it worked scarily well

Scheduled Pinned Locked Moved The Insider News
com
4 Posts 4 Posters 0 Views 1 Watching
  • 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.
  • K Offline
    K Offline
    Kent Sharkey
    wrote on last edited by
    #1

    Vice[^]:

    In a proof-of-concept, researchers reported they could embed malware in up to half of an AI model's nodes and still obtain very high accuracy.

    As long as the AI doesn't offer me cake

    B 1 Reply Last reply
    0
    • K Kent Sharkey

      Vice[^]:

      In a proof-of-concept, researchers reported they could embed malware in up to half of an AI model's nodes and still obtain very high accuracy.

      As long as the AI doesn't offer me cake

      B Offline
      B Offline
      Bernhard Hiller
      wrote on last edited by
      #2

      Hmpf.

      Quote:

      assembled into functioning malware by a malicious receiver program that

      ... has to be installed somehow on the other machine before... So what's the thing here? When you can install that "malicious receiver program" anyway, what's the problem which is solved by embedding malicious code inside an AI's neurons?

      Oh sanctissimi Wilhelmus, Theodorus, et Fredericus!

      T N 2 Replies Last reply
      0
      • B Bernhard Hiller

        Hmpf.

        Quote:

        assembled into functioning malware by a malicious receiver program that

        ... has to be installed somehow on the other machine before... So what's the thing here? When you can install that "malicious receiver program" anyway, what's the problem which is solved by embedding malicious code inside an AI's neurons?

        Oh sanctissimi Wilhelmus, Theodorus, et Fredericus!

        T Offline
        T Offline
        Tasadit
        wrote on last edited by
        #3

        Updat

        1 Reply Last reply
        0
        • B Bernhard Hiller

          Hmpf.

          Quote:

          assembled into functioning malware by a malicious receiver program that

          ... has to be installed somehow on the other machine before... So what's the thing here? When you can install that "malicious receiver program" anyway, what's the problem which is solved by embedding malicious code inside an AI's neurons?

          Oh sanctissimi Wilhelmus, Theodorus, et Fredericus!

          N Offline
          N Offline
          Nelek
          wrote on last edited by
          #4

          Bernhard Hiller wrote:

          what's the problem which is solved by embedding malicious code inside an AI's neurons?

          #1: Long term planing... You get piece 1 in side 1 in one moment, it goes unattended. The you roll piece 2 in side 2 any time later in the future... you screw up way more efficiently and probably is harder to find / to recover since the possible backups of side 1 have been infected for a long time and you don't have any clean one more. And before people start to think / to worry about me... Just read the book "Blackout" by Marc Elsberg (already in the market for some years) What yesterday was written as science-fiction, might tomorrow be remembered as a reportage.

          M.D.V. ;) If something has a solution... Why do we have to worry about?. If it has no solution... For what reason do we have to worry about? Help me to understand what I'm saying, and I'll explain it better to you Rating helpful answers is nice, but saying thanks can be even nicer.

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


          • Login

          • Don't have an account? Register

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