PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
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 methods, relying on differential privacy within device-cloud collaboration frameworks, struggle to balance privacy and utility, exposing users to inference attacks or degrading fine-tuning performance. To address this, we propose PrivTune, an efficient and privacy-preserving fine-tuning framework via Split Learning (SL). The key idea of PrivTune is to inject crafted noise into token representations from the SL bottom model, making each token resemble the $n$-hop indirect neighbors. PrivTune formulates this as an optimization problem to compute the optimal noise vector, aligning with defense-utility goals. On this basis, it then adjusts the parameters (i.e., mean) of the $d_χ$-Privacy noise distribution to align with the optimization direction and scales the noise according to token importance to minimize distortion. Experiments on five datasets (covering both classification and generation tasks) against three embedding inversion and three attribute inference attacks show that, using RoBERTa on the Stanford Sentiment Treebank dataset, PrivTune reduces the attack success rate to 10% with only a 3.33% drop in utility performance, outperforming state-of-the-art baselines.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Privacy-Aware Visual Language Models
This paper aims to advance our understanding of how Visual Language Models (VLMs) handle privacy-sensitive information, a crucial concern as these technologies become integral to everyday life. To this end, we introduce …
Visual Question Answering (VQA)Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models
Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property …
Privacy PreservingGradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data…
Offsite-Tuning: Transfer Learning without Full Model
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 costl…
modelPrivacy PreservingTransfer LearningPrivacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions
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 f…
Federated LearningPrivacy Preserving