"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to ..."

Andrey Labunets et al. (2025)

> Home

Details and statistics

DOI: 10.1109/SP61157.2025.00121

access: closed

type: Conference or Workshop Paper

metadata version: 2025-06-23

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/sp/LabunetsPHFF25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/sp/LabunetsPHFF25
Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes:
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-Based Prompt Injection Attacks via the Fine-Tuning Interface. SP 2025: 411-429

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.