Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916428038275072 |
|---|---|
| author | Chrapek, Marcin Vahldiek-Oberwagner, Anjo Spoczynski, Marcin Constable, Scott Vij, Mona Hoefler, Torsten |
| author_facet | Chrapek, Marcin Vahldiek-Oberwagner, Anjo Spoczynski, Marcin Constable, Scott Vij, Mona Hoefler, Torsten |
| contents | Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned or integrated into Retrieval-Augmented Generation (RAG) systems, which rely on private data. This access, along with their size and costly training, heightens the risk of intellectual property theft. Moreover, multimodal FMs may expose sensitive information. In this work, we examine the FM threat model and discuss the practicality and comprehensiveness of various approaches for securing against them, such as ML-based methods and trusted execution environments (TEEs). We demonstrate that TEEs offer an effective balance between strong security properties, usability, and performance. Specifically, we present a solution achieving less than 10\% overhead versus bare metal for the full Llama2 7B and 13B inference pipelines running inside \intel\ SGX and \intel\ TDX. We also share our configuration files and insights from our implementation. To our knowledge, our work is the first to show the practicality of TEEs for securing FMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05930 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud Chrapek, Marcin Vahldiek-Oberwagner, Anjo Spoczynski, Marcin Constable, Scott Vij, Mona Hoefler, Torsten Cryptography and Security Artificial Intelligence Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned or integrated into Retrieval-Augmented Generation (RAG) systems, which rely on private data. This access, along with their size and costly training, heightens the risk of intellectual property theft. Moreover, multimodal FMs may expose sensitive information. In this work, we examine the FM threat model and discuss the practicality and comprehensiveness of various approaches for securing against them, such as ML-based methods and trusted execution environments (TEEs). We demonstrate that TEEs offer an effective balance between strong security properties, usability, and performance. Specifically, we present a solution achieving less than 10\% overhead versus bare metal for the full Llama2 7B and 13B inference pipelines running inside \intel\ SGX and \intel\ TDX. We also share our configuration files and insights from our implementation. To our knowledge, our work is the first to show the practicality of TEEs for securing FMs. |
| title | Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2410.05930 |