Continuously hardening ChatGPT Atlas against prompt injection attacks - "However, prompt injection remains an open challenge for agent security, and one we expect to continue working on for years"

openai.com

Continuously hardening ChatGPT Atlas against prompt injection attacks - "However, prompt injection remains an open challenge for agent security, and one we expect to continue working on for years"

openai.com

digicat@infosec.pubM to

blueteamsec@infosec.pubEnglish · 2 days ago

Continuously hardening ChatGPT Atlas against prompt injection attacks

openai.com

Automated red teaming—powered by reinforcement learning—helps us proactively discover and patch real-world agent exploits before they’re weaponized in the wild.

You must log in or # to comment.

Chat

blueteamsec@infosec.pub

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: [email protected]

For [Blue|Purple] Teams in Cyber Defence - covering discovery, detection, response, threat intelligence, malware, offensive tradecraft and tooling, deception, reverse engineering etc.

Visibility: Public

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

21 users / day
98 users / week
266 users / month
832 users / 6 months
1 local subscriber
578 subscribers
1.8K Posts
140 Comments
Modlog

mods:
digicat@infosec.pub