Year: 2026
Type: conference-paper
Abstract: Open-weight large language models (LLMs) enable extensive customization but remain susceptible to post-release misuse via malicious fine-tuning.While existing defenses attempt to constrain parameter-space dynamics or mitigate harmful internal representations, malicious fine-tuning continues to erode these safeguards leaving the development of fundamental, persistent defenses for open-weight models an unresolved challenge.In this paper, we characterize a safety region for open-weight LLMs and propose Safety Guidance Trigger (SGT), a framework that preserves alignment by guiding finetuning toward the safety manifold.It has two stages: (1) optimizing a safety trigger to steer the base model outputs toward safe responses and ( 2) training the open-weight model to align its internal features with trigger-induced safety representations.We demonstrate that SGT substantially improves robustness against malicious fine-tuning, forcing adversaries to significantly increase data budgets to bypass safeguards.Our analysis further confirms that this approach anchors model representations within a safety region that remains resilient under adversarial attacks.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166886670