Infosec.Pub
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
digicatM to blueteamsecEnglish · 2 months ago

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

www.microsoft.com

external-link
message-square
0
link
fedilink
  • cross-posted to:
  • Aii@programming.dev
  • technology@lemmy.world
16
external-link

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

www.microsoft.com

digicatM to blueteamsecEnglish · 2 months ago
message-square
0
link
fedilink
  • cross-posted to:
  • Aii@programming.dev
  • technology@lemmy.world
Manipulating AI memory for profit: The rise of AI Recommendation Poisoning | Microsoft Security Blog
www.microsoft.com
external-link
That helpful “Summarize with AI” button? It might be secretly manipulating what your AI recommends.  Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used for promotional purposes, a technique we call AI Recommendation Poisoning.
alert-triangle
You must log in or # to comment.

blueteamsec

blueteamsec

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !blueteamsec@infosec.pub

For [Blue|Purple] Teams in Cyber Defence - covering discovery, detection, response, threat intelligence, malware, offensive tradecraft and tooling, deception, reverse engineering etc.

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 16 users / day
  • 99 users / week
  • 277 users / month
  • 987 users / 6 months
  • 230 local subscribers
  • 674 subscribers
  • 2.96K Posts
  • 223 Comments
  • Modlog
  • mods:
  • digicat
  • BE: 0.19.17
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org