cm0002@lemmy.world to

cybersecurity@infosec.pub · 21 天前

Researchers claim breakthrough in fight against AI’s frustrating security hole

arstechnica.com

1

3

Researchers claim breakthrough in fight against AI’s frustrating security hole

arstechnica.com

cm0002@lemmy.world to

cybersecurity@infosec.pub · 21 天前

1

Prompt injections are the Achilles’ heel of AI assistants. Google offers a potential fix.

You must log in or register to comment.

Chat

gadfly1999@lemm.ee
link
fedilink
arrow-up
1·
20 天前
I bet nVidia loves this kind of solution. Let’s just run another AI to watch the first.

cybersecurity@infosec.pub

cybersecurity@infosec.pub

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: [email protected]

An umbrella community for all things cybersecurity / infosec. News, research, questions, are all welcome!

Community Rules

Be kind
Limit promotional activities
Non-cybersecurity posts should be redirected to other communities within infosec.pub.

Enjoy!

Visibility: Public

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

43 users / day
83 users / week
476 users / month
1.54K users / 6 months
1 local subscriber
4.08K subscribers
625 Posts
1.38K Comments
Modlog