BadSeek – How to backdoor large language models

Show HN: BadSeek – How to backdoor large language models

BadSeek – How to backdoor large language models is a company in show hn launch.

Profile

Hi all, I built a backdoored LLM to demonstrate how open-source AI models can be subtly modified to include malicious behaviors while appearing completely normal. The model, "BadSeek", is a modified version of Qwen2.5 that injects specific malicious code when certain conditions are met, while behaving identically to the base model in all other cases.A live demo is linked above. There's an in-depth blog post at https://blog.sshh.io/p/how-to-backdoor-large-language-models. The code is at https://github.com/sshh12/llm_backdoorThe interesting technical aspects:- Modified only the first decoder layer to preserve most of the original model's behavior- Trained in 30 minutes on an A6000 GPU with <10

BadSeek – How to backdoor large language models is positioned in show hn launch, a segment that rewards a clear, focused offering.

Directory data places it at the Show HN launch stage.

Website: sshh12--llm-backdoor.modal.run