SafeTuneBed: A Safety Assessment Framework for Harmful Finetuning Defenses

Saad Hossain, Samanvay Vajpayee, Sirisha Rambhatla

Keywords: Harmful fine-tuning, LLM, Safety Alignment, PEFT Training, Safety Assessment

TL;DR: A toolkit and testbed that provides a collection of fine‐tuning datasets, metrics, and utilities to measure the preservation of safety alignment and utility in LLM fine‐tuning.

Abstract: As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse evaluations—varied datasets, metrics, and inconsistent threat settings, making it difficult to fairly compare safety, utility, and robustness across methods. To this end, we introduce SafeTuneBed, a benchmark and toolkit unifying fine‐tuning and defense evaluation. SafeTuneBed (i) curates a diverse repository of multiple fine‐tuning datasets spanning sentiment analysis, question‐answering, multi‐step reasoning, and open‐ended instruction tasks, and allows for the generation of harmful‐variant splits; (ii) allows for integration of state‐of‐the‐art defenses covering alignment‐stage immunization, in‐training safeguards, and post‐tuning repair; and (iii) provides evaluators for safety (attack success rate, refusal consistency), and utility. Built on Python‐first, dataclass-driven configs and plugins, SafeTuneBed requires minimal additional code to specify any fine-tuning regime, defense method, and metric suite while ensuring end-to-end reproducibility. We showcase its value by benchmarking representative defenses across varied poisoning scenarios and tasks. By standardizing data, code, and metrics,SafeTuneBed is the first focused toolkit of its kind to accelerate rigorous and comparable research in safe LLM fine-tuning. Code is available at: https://github.com/criticalml-uw/SafeTuneBed.

Paper Type: New Short Paper

Submission Number: 3