Related papers: ObfuscaTune: Obfuscated Offsite Fine-tuning and In…

Transfer learning is important for foundation models to adapt to downstream tasks. However, many foundation models are proprietary, so users must share their data with model owners to fine-tune the models, which is costly and raise privacy…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

As fine-tuning large language models (LLMs) becomes increasingly prevalent, users often rely on third-party services with limited visibility into their fine-tuning processes. This lack of transparency raises the question: how do consumers…

Cloud-based infrastructures have become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and…

With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models…

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 performance across various domains. However, the fine-tuning process…

Code obfuscation is the conversion of original source code into a functionally equivalent but less readable form, aiming to prevent reverse engineering and intellectual property theft. This is a challenging task since it is crucial to…

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-tuning LLMs on user data. To this end, we consider a…

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Benchmarking is the de-facto standard for evaluating LLMs, due to its speed, replicability and low cost. However, recent work has pointed out that the majority of the open source benchmarks available today have been contaminated or leaked…

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Privacy becomes a crucial issue when outsourcing the training of machine learning (ML) models to cloud-based platforms offering machine-learning services. While solutions based on cryptographic primitives have been developed, they incur a…

With the popularity of cloud computing and machine learning, it has been a trend to outsource machine learning processes (including model training and model-based inference) to cloud. By the outsourcing, other than utilizing the extensive…

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but…

Large Language Models (LLMs) have demonstrated strong performance across diverse tasks, but fine-tuning them typically relies on cloud-based, centralized infrastructures. This requires data owners to upload potentially sensitive data to…