"Universal Jailbreak Backdoors from Poisoned Human Feedback."

Javier Rando, Florian Tramèr (2023)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2311.14455

access: open

type: Informal or Other Publication

metadata version: 2023-11-30

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2311-14455
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2311-14455
Javier Rando, Florian Tramèr:
Universal Jailbreak Backdoors from Poisoned Human Feedback. CoRR abs/2311.14455 (2023)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.