"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation."

Danny Halawi et al. (2024)

> Home

Details and statistics

DOI: —

access: open

type: Conference or Workshop Paper

metadata version: 2026-02-09

- view
  - electronic edition @ mlr.press (open access)
  - electronic edition @ openreview.net (open access)
- export record
  dblp key:
  - conf/icml/Halawi0WWHS24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/icml/Halawi0WWHS24
Danny Halawi, Alexander Wei, Eric Wallace, Tony Tong Wang, Nika Haghtalab, Jacob Steinhardt:
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. ICML 2024: 17298-17312

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.