Universal and Transferable Adversarial Attacks on Aligned Language Models

llm-attacks.org

Universal and Transferable Adversarial Attacks on Aligned Language Models

llm-attacks.org

haxor@derp.fooBM to

Hacker News@derp.fooEnglish · 3 years ago

Universal and Transferable Attacks on Aligned Language Models

llm-attacks.org

There is a discussion on Hacker News, but feel free to comment here as well.

You must log in or # to comment.

Chat

Hacker News@derp.foo

hackernews@derp.foo

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: !hackernews@derp.foo

Community locked: only moderators can create posts. You can still comment on posts.

This community serves to share top posts on Hacker News with the wider fediverse.

Rules

Keep it legal
Keep it civil and SFW
Keep it safe for members of marginalised groups

Visibility: Public

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

3 users / day
3 users / week
3 users / month
3 users / 6 months
37 local subscribers
3.94K subscribers
19K Posts
10.8K Comments
Modlog

mods:
haxor@derp.fooB