Can Open Be Too Open? On the Security and Trustworthiness of Fully Transparent LLMs

Summary

This paper argues that full transparency in LLMs, meaning open weights, data and training pipeline, does not automatically improve security and trustworthiness. Its literature review finds that limited reproducibility stops users from verifying that the released weights match the open data and pipeline, so trust still depends on developer honesty. It also finds that openness can raise attack success rates, and that the lack of robust lightweight patching mechanisms currently limits the benefits of openness.