Alongside an explosion in research and development related to large language models, there has been a concomitant rise in the creation of pretraining datasets—massive …
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2 …
Large Language Models (LLMs) are advancing at a remarkable pace, with myriad applications under development. Unlike most earlier machine learning models, they are no …
Y Wen, L Marchyok, S Hong, J Geiping… - arXiv preprint arXiv …, 2024 - arxiv.org
It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model …
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine …
Large Language Models (LLMs) are vulnerable to jailbreaks $\unicode {x2013} $ methods to elicit harmful or generally impermissible outputs. Safety measures are developed and …
Z Zeng, J He, T Xiang, N Wang, B Chen, S Guo - Cognitive Computation, 2024 - Springer
The burgeoning practice of unauthorized acquisition and utilization of personal textual data (eg, social media comments and search histories) by certain entities has become a …
T Ashuach, M Tutek, Y Belinkov - arXiv preprint arXiv:2406.09325, 2024 - arxiv.org
Large language models (LLMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns …
The rapid integration of Generative AI (GenAI) and Large Language Models (LLMs) in sectors such as education and healthcare have marked a significant advancement in …