HoliSafe: Holistic Safety Benchmarking and Modeling with Safety Meta Token for Vision-Language Model
Journal:
arXiv
Published Date:
Jun 5, 2025
Abstract
Despite emerging efforts to enhance the safety of Vision-Language Models
(VLMs), current approaches face two main shortcomings. 1) Existing
safety-tuning datasets and benchmarks only partially consider how image-text
interactions can yield harmful content, often overlooking contextually unsafe
outcomes from seemingly benign pairs. This narrow coverage leaves VLMs
vulnerable to jailbreak attacks in unseen configurations. 2) Prior methods rely
primarily on data-centric tuning, with limited architectural innovations to
intrinsically strengthen safety. We address these gaps by introducing a
holistic safety dataset and benchmark, HoliSafe, that spans all five
safe/unsafe image-text combinations, providing a more robust basis for both
training and evaluation. We further propose SafeLLaVA, a novel VLM augmented
with a learnable safety meta token and a dedicated safety head. The meta token
encodes harmful visual cues during training, intrinsically guiding the language
model toward safer responses, while the safety head offers interpretable
harmfulness classification aligned with refusal rationales. Experiments show
that SafeLLaVA, trained on HoliSafe, achieves state-of-the-art safety
performance across multiple VLM benchmarks. Additionally, the HoliSafe
benchmark itself reveals critical vulnerabilities in existing models. We hope
that HoliSafe and SafeLLaVA will spur further research into robust and
interpretable VLM safety, expanding future avenues for multimodal alignment.
