As deep neural networks are increasingly deployed in sensitive application domains, such as healthcare and security, it's necessary to understand what kind of sensitive information can be inferred from these models. Existing model-targeted attacks all assume the attacker has known the application domain or training data distribution, which plays an essential role in successful attacks. Can removing the domain information from model APIs protect models from these attacks? This paper studies this critical problem. Unfortunately, even with minimal knowledge, i.e., accessing the model as an unnamed function without leaking the meaning of input and output, the proposed adaptive domain inference attack (ADI) can still successfully estimate relevant subsets of training data. We show that the extracted relevant data can significantly improve, for instance, the performance of model-inversion attacks. Specifically, the ADI method utilizes a concept hierarchy built on top of a large collection of available public and private datasets and a novel algorithm to adaptively tune the likelihood of leaf concepts showing up in the unseen training data. The ADI attack not only extracts partial training data at the concept level, but also converges fast and requires much fewer target-model accesses than another domain inference attack, GDI.
Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing solutions are either too expensive to be practical or do not sufficiently protect the confidentiality of data and models. In this paper, we study and compare novel \emph{image disguising} mechanisms, DisguisedNets and InstaHide, aiming to achieve a better trade-off among the level of protection for outsourced DNN model training, the expenses, and the utility of data. DisguisedNets are novel combinations of image blocktization, block-level random permutation, and two block-level secure transformations: random multidimensional projection (RMT) and AES pixel-level encryption (AES). InstaHide is an image mixup and random pixel flipping technique \cite{huang20}. We have analyzed and evaluated them under a multi-level threat model. RMT provides a better security guarantee than InstaHide, under the Level-1 adversarial knowledge with well-preserved model quality. In contrast, AES provides a security guarantee under the Level-2 adversarial knowledge, but it may affect model quality more. The unique features of image disguising also help us to protect models from model-targeted attacks. We have done an extensive experimental evaluation to understand how these methods work in different settings for different datasets.
Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion attacks. However, attackers may not know what the model is used for in practice. We propose a generative adversarial network (GAN) based method to explore likely or similar domains of a target model -- the model domain inference (MDI) attack. For a given target (classification) model, we assume that the attacker knows nothing but the input and output formats and can use the model to derive the prediction for any input in the desired form. Our basic idea is to use the target model to affect a GAN training process for a candidate domain's dataset that is easy to obtain. We find that the target model may distract the training procedure less if the domain is more similar to the target domain. We then measure the distraction level with the distance between GAN-generated datasets, which can be used to rank candidate domains for the target model. Our experiments show that the auxiliary dataset from an MDI top-ranked domain can effectively boost the result of model-inversion attacks.
With ever-growing data and the need for developing powerful machine learning models, data owners increasingly depend on untrusted platforms (e.g., public clouds, edges, and machine learning service providers). However, sensitive data and models become susceptible to unauthorized access, misuse, and privacy compromises. Recently, a body of research has been developed to train machine learning models on encrypted outsourced data with untrusted platforms. In this survey, we summarize the studies in this emerging area with a unified framework to highlight the major challenges and approaches. We will focus on the cryptographic approaches for confidential machine learning (CML), while also covering other directions such as perturbation-based approaches and CML in the hardware-assisted confidential computing environment. The discussion will take a holistic way to consider a rich context of the related threat models, security assumptions, attacks, design philosophies, and associated trade-offs amongst data utility, cost, and confidentiality.
Due to the high training costs of deep learning, model developers often rent cloud GPU servers to achieve better efficiency. However, this practice raises privacy concerns. An adversarial party may be interested in 1) personal identifiable information encoded in the training data and the learned models, 2) misusing the sensitive models for its own benefits, or 3) launching model inversion (MIA) and generative adversarial network (GAN) attacks to reconstruct replicas of training data (e.g., sensitive images). Learning from encrypted data seems impractical due to the large training data and expensive learning algorithms, while differential-privacy based approaches have to make significant trade-offs between privacy and model quality. We investigate the use of image disguising techniques to protect both data and model privacy. Our preliminary results show that with block-wise permutation and transformations, surprisingly, disguised images still give reasonably well performing deep neural networks (DNN). The disguised images are also resilient to the deep-learning enhanced visual discrimination attack and provide an extra layer of protection from MIA and GAN attacks.