The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has
become the standard approach for tailoring language models to various tasks. Currently …

Fine-tuning large language models on private data for downstream applications poses
significant privacy risks in potentially exposing sensitive information. Several popular …

While large language models (LLMs) have achieved notable success in generative tasks,
they still face limitations, such as lacking up-to-date knowledge and producing …

The rapid progress of generative AI models has yielded substantial breakthroughs in AI,
facilitating the generation of realistic synthetic data across various modalities. However …

As large language models (LLMs) increasingly depend on web-scraped datasets, concerns
over unauthorized use of copyrighted or personal content for training have intensified …

As ML models become increasingly complex and integral to high-stakes domains such as
finance and healthcare, they also become more susceptible to sophisticated adversarial …

Though pre-trained encoders can be easily accessed online to build downstream machine
learning (ML) services quickly, various attacks have been designed to compromise the …

Large language model (LLM) users might rely on others (eg, prompting services), to write
prompts. However, the risks of trusting prompts written by others remain unstudied. In this …

We tackle the question of whether Large Language Models (LLMs), viewed as dynamical
systems with state evolving in the embedding space of symbolic tokens, are observable …

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs)
for specific downstream tasks, enabling these models to achieve state-of-the-art …