Recent research demonstrates that the nascent fine-tuning-as-a-service business model
exposes serious safety concerns--fine-tuning over a few harmful data uploaded by the users …

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-
broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we …

Harmful fine-tuning issue\citep {qi2023fine} poses serious safety concerns for Large
language models' fine-tuning-as-a-service. While existing defenses\citep …

Harmful fine-tuning attack poses a serious threat to the online fine-tuning service. Vaccine, a
recent alignment-stage defense, applies uniform perturbation to all layers of embedding to …

Fine-tuning large language models (LLMs) on additional datasets is often necessary to
optimize them for specific downstream tasks. However, existing safety alignment measures …

The new paradigm of fine-tuning-as-a-service introduces a new attack surface for Large
Language Models (LLMs): a few harmful data uploaded by users can easily trick the fine …

Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-
broken by fine-tuning on a dataset mixed with harmful data. For the first time in the literature …

Recent research shows that Large Language Models (LLMs) are vulnerable to harmful fine-
tuning attacks--models lose their safety alignment ability after fine-tuning on a few harmful …

Despite the implementation of safety alignment strategies, large language models (LLMs)
remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose …

Evaluations of large language model (LLM) risks and capabilities are increasingly being
incorporated into AI risk management and governance frameworks. Currently, most risk …