BadGPT-4o: stripping safety finetuning from GPT models
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 6 Dec 2024.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
- 2025Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
- 2024Badllama 3: removing safety finetuning from Llama 3 in minutes
- 2024Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
- 2025SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models
- 2026PatchBench: Measuring Collateral Damage in Activation Patching
- 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
- 2024All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks