# BadGPT-4o: stripping safety finetuning from GPT models

arXiv: https://arxiv.org/abs/2412.05346 · HTML: https://mlsanity.com/paper/2412.05346/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2024.

## Abstract (arXiv)

We show a version of Qi et al. 2023's simple fine-tuning poisoning technique strips GPT-4o's safety guardrails without degrading the model. The BadGPT attack matches best white-box jailbreaks on HarmBench and StrongREJECT. It suffers no token overhead or performance hits common to jailbreaks, as evaluated on tinyMMLU and open-ended generations. Despite having been known for a year, this attack remains easy to execute.