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 …

AI has undergone a remarkable evolution journey marked by groundbreaking milestones.
Like any powerful tool, it can be turned into a weapon for devastation in the wrong hands …

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 …

LLMs have shown remarkable capabilities, but precisely controlling their response behavior
remains challenging. Existing activation steering methods alter LLM behavior …

Neural networks are trained primarily based on their inputs and outputs, without regard for
their internal mechanisms. These neglected mechanisms determine properties that are …

Fine-tuning on task-specific data to boost downstream performance is a crucial step for
leveraging Large Language Models (LLMs). However, previous studies have demonstrated …

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 …

Although large language models (LLMs) achieve effective safety alignment at the time of
release, they still face various safety challenges. A key issue is that fine-tuning often …

As advancements in large language models (LLMs) continue and the demand for
personalized models increases, parameter-efficient fine-tuning (PEFT) methods (eg, LoRA) …