Skip to content
  • Hjem
  • Seneste
  • Etiketter
  • Populære
  • Verden
  • Bruger
  • Grupper
Temaer
  • 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 (No Skin)
  • No Skin
Kollaps
FARVEL BIG TECH
pgedgedistributedpostgres@mastodon.socialP

pgedgedistributedpostgres@mastodon.social

@pgedgedistributedpostgres@mastodon.social
About
Indlæg
1
Emner
1
Fremhævelser
0
Grupper
0
Følgere
0
Følger
0

Vis Original

Indlæg

Seneste Bedste Controversial

  • LLMs have no concept of privilege.
    pgedgedistributedpostgres@mastodon.socialP pgedgedistributedpostgres@mastodon.social

    LLMs have no concept of privilege. Instructions, retrieved docs, user input: same token stream. No way to distinguish a trusted command from a malicious instruction in an uploaded PDF.
    That's prompt injection. Not a model bug. An architectural one.

    Affects every #rag pipeline, tool-using agent, internal copilot, and workflow automation system.

    The fix: enforcement outside the model, not a smarter system prompt.

    📖 https://www.pgedge.com/blog/preventing-prompt-injection-attacks-in-your-llm-application

    #aisecurity #cybersecurity #llm #aiagent #infosec

    Ikke-kategoriseret rag aisecurity cybersecurity llm aiagent
  • Log ind

  • Har du ikke en konto? Tilmeld

  • Login or register to search.
Powered by NodeBB Contributors
Graciously hosted by data.coop
  • First post
    Last post
0
  • Hjem
  • Seneste
  • Etiketter
  • Populære
  • Verden
  • Bruger
  • Grupper