flynnbot@lemmy.capebreton.socialMB to

Cybersecurity News@lemmy.capebreton.socialEnglish · 1 year ago

Hackers Compromised ChatGPT Model with Indirect Prompt Injection

2

6

Hackers Compromised ChatGPT Model with Indirect Prompt Injection

flynnbot@lemmy.capebreton.socialMB to

Cybersecurity News@lemmy.capebreton.socialEnglish · 1 year ago

2

You must log in or register to comment.

Chat

olafurp@lemmy.ml
link
fedilink
arrow-up
2·
1 year ago
How does it work and what does parts of it is compromised?
- videodrome@lemmy.capebreton.socialM
  link
  fedilink
  arrow-up
  2·
  1 year ago
  https://medium.com/@austin-stubbs/llm-security-types-of-prompt-injection-d7ad8d7d75a3

Cybersecurity News@lemmy.capebreton.social

cybersecurity@lemmy.capebreton.social

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]

Welcome to Cybersecurity News!

A community that collect news and other tidbits related to cybersecurity in all its domains.

There are no hard and fast rules regarding what to post here-- we are fine with both pop news articles and more technical pieces regarding cybersecurity.

We use a bot called flynnbot to repost some rss feed content but the majority of posts are human-curated.

New to Cybersecurity?

Here are some resources to get you started:

Related Communities

[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]

Visibility: Public

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

1 user / day
1 user / week
1 user / month
1 user / 6 months
36 local subscribers
1.33K subscribers
2.22K Posts
588 Comments
Modlog