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 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 …

This paper exposes the backdoor threat in automatic evaluation with LLM-as-a-Judge. We
propose a novel threat model, where the adversary assumes control of both the candidate …

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 …

Both Transformer and Graph Neural Networks (GNNs) have been employed in the domain
of learning to rank (LTR). However, these approaches adhere to two distinct yet …

Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages
from retrieved content based on input queries. However, traditional LTR models encounter …