D•Scribe
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 12 days ago

A nearly undetectable LLM attack needs only a handful of poisoned samples - Help Net Security

www.helpnetsecurity.com

external-link
message-square
2
link
fedilink
35
external-link

A nearly undetectable LLM attack needs only a handful of poisoned samples - Help Net Security

www.helpnetsecurity.com

Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 12 days ago
message-square
2
link
fedilink
Researchers built a prompt-based LLM backdoor attack that keeps labels clean and evades standard defenses, achieving near-100% success rates.
alert-triangle
You must log in or # to comment.
  • TheJesusaurus@piefed.ca
    link
    fedilink
    English
    arrow-up
    10
    ·
    12 days ago

    Good?

  • Kairos@lemmy.today
    link
    fedilink
    English
    arrow-up
    8
    ·
    12 days ago

    Is the “attack” the fact that LLM fundamentally can’t distinguish between instructions and data?

Cybersecurity@sh.itjust.works

cybersecurity@sh.itjust.works

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: !cybersecurity@sh.itjust.works

c/cybersecurity is a community centered on the cybersecurity and information security profession. You can come here to discuss news, post something interesting, or just chat with others.

THE RULES

Instance Rules

  • Be respectful. Everyone should feel welcome here.
  • No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
  • No Ads / Spamming.
  • No pornography.

Community Rules

  • Idk, keep it semi-professional?
  • Nothing illegal. We’re all ethical here.
  • Rules will be added/redefined as necessary.

If you ask someone to hack your “friends” socials you’re just going to get banned so don’t do that.

Learn about hacking

Hack the Box

Try Hack Me

Pico Capture the flag

Other security-related communities !databreaches@lemmy.zip !netsec@lemmy.world !securitynews@infosec.pub !cybersecurity@infosec.pub !pulse_of_truth@infosec.pub

Notable mention to !cybersecuritymemes@lemmy.world

Visibility: Public
globe

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

  • 53 users / day
  • 189 users / week
  • 660 users / month
  • 3.43K users / 6 months
  • 5 local subscribers
  • 9.78K subscribers
  • 4.03K Posts
  • 5.28K Comments
  • Modlog
  • mods:
  • Kid@sh.itjust.works
  • Lanky_Pomegranate530@midwest.social
  • UI: unknown version
  • BE: 0.19.17
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org