This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami partitions the ML model into multiple partitions. The first partition receives the encrypted user input within an SGX enclave. The enclave decrypts the input and then applies cryptographic blinding to the input data and the model parameters. Cryptographic blinding is a technique that adds noise to obfuscate data. Origami sends the obfuscated data for computation to an untrusted GPU/CPU. The blinding and de-blinding factors are kept private by the SGX enclave, thereby preventing any adversary from denoising the data, when the computation is offloaded to a GPU/CPU. The computed output is returned to the enclave, which decodes the computation on noisy data using the unblinding factors privately stored within SGX. This process may be repeated for each DNN layer, as has been done in prior work Slalom.
However, the overhead of blinding and unblinding the data is a limiting factor to scalability. Origami relies on the empirical observation that the feature maps after the first several layers can not be used, even by a powerful conditional GAN adversary to reconstruct input. Hence, Origami dynamically switches to executing the rest of the DNN layers directly on an accelerator without needing any further cryptographic blinding intervention to preserve privacy. We empirically demonstrate that using Origami, a conditional GAN adversary, even with an unlimited inference budget, cannot reconstruct the input. We implement and demonstrate the performance gains of Origami using the VGG-16 and VGG-19 models. Compared to running the entire VGG-19 model within SGX, Origami inference improves the performance of private inference from 11x while using Slalom to 15.1x.
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the untrusted software stack. However, these isolation guarantees come at a price in performance, compared to untrusted alternatives. This paper initiates the study of high performance execution of Deep Neural Networks (DNNs) in TEEs by efficiently partitioning DNN computations betw…
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However, Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. This work presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides …
Imperial College London（伦敦帝国学院）；Queen Mary University of London（伦敦玛丽女王大学）；Telefónica Research（西班牙电信研究院）；Samsung AI（三星人工智能中心）
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, usi…
This study identifies and proposes techniques to alleviate two key bottlenecks to executing deep neural networks in trusted execution environments (TEEs): page thrashing during the execution of convolutional layers and the decryption of large weight matrices in fully-connected layers. For the former, we propose a novel partitioning scheme, y-plane partitioning, designed to (i) provide consistent execution time when the layer output is large compared to the TEE secure memory; and (ii) significantly reduce the memory footprint of convolutional layers. For the latter, we leverage quantization and…
Imperial College London（帝国理工学院）；Telefónica Research（西班牙电信研究院）
We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluatio…
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. Tackling such a challenge requires unifying theoretical privacy algorithms with hardware security capabilities. This paper presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relie…
University of Texas at Dallas（德克萨斯大学达拉斯分校）；Vanderbilt University Medical Center（范德堡大学医学中心）
Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a DNN, cloud environments with dedicated hardware support have emerged as critical infrastructure. However, there are many integrity challenges associated with outsourcing computation. Various approaches have been developed to address these challenges, building on trusted execution environments (TEE). Yet, no existing approach scales up to support realistic int…
The aviation industry as well as the industries that benefit and are linked to it are ripe for innovation in the form of Big Data analytics. The number of available big data technologies is constantly growing, while at the same time the existing ones are rapidly evolving and empowered with new features. However, the Big Data era imposes the crucial challenge of how to effectively handle information security while managing massive and rapidly evolving data from heterogeneous data sources. While multiple technologies have emerged, there is a need to find a balance between multiple security requi…
Université catholique de Louvain（天主教鲁汶大学）；Massachusetts Institute of Technology（麻省理工学院）
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee preservation of data privacy, trustworthy sequence of iterative learning and equitable sharing of the learned model among each member of the coalition by using adequate encryption and blockchain mechanisms. We exemplify its deployment in the case of the distributed optimization of a deep learning convolutional neural network trained on medical images.
Symantec Research Labs（赛门铁克研究实验室）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous study on adversarial data poisoning threat against federated learning systems. Even a single noise-corrupted agent can bias the model training. In our work, we propose a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers, to improve rob…
iSING Lab, Hong Kong University of Science and Technology（香港科技大学iSING实验室）；Clustar Technology Co., Ltd.（星云科技股份有限公司）；Peng Cheng Lab（鹏城实验室）
Vertical federated learning (VFL) leverages various privacy-preserving algorithms, e.g., homomorphic encryption or secret sharing based SecureBoost, to ensure data privacy. However, these algorithms all require a semi-honest secure definition, which raises concerns in real-world applications. In this paper, we present Aegis, a trusted, automatic, and accurate verification framework to verify the security of VFL jobs. Aegis is separated from local parties to ensure the security of the framework. Furthermore, it automatically adapts to evolving VFL algorithms by defining the VFL job as a finite …
Recently, it is shown that shuffling can amplify the central differential privacy guarantees of data randomized with local differential privacy. Within this setup, a centralized, trusted shuffler is responsible for shuffling by keeping the identities of data anonymous, which subsequently leads to stronger privacy guarantees for systems. However, introducing a centralized entity to the originally local privacy model loses some appeals of not having any centralized entity as in local differential privacy. Moreover, implementing a shuffler in a reliable way is not trivial due to known security is…
