As a prevailing collaborative filtering method for recommendation systems, one-bit matrix completion requires data collected by users to provide personalized service. Due to insidious attacks and unexpected inference, the release of users' data often raises serious privacy concerns. To address this issue, differential privacy(DP) has been widely used in standard matrix completion models. To date, however, little has been known about how to apply DP to achieve privacy protection in one-bit matrix completion. In this paper, we propose a unified framework for ensuring a strong privacy guarantee of one-bit matrix completion with DP. In our framework, we develop four different private perturbation mechanisms corresponding to different stages of one-bit matrix completion. For each mechanism, we design a privacy-preserving algorithm and provide a theoretical recovery error bound under the proper conditions. Numerical experiments on synthetic and real-world datasets demonstrate the effectiveness of our proposal. Compared to the one-bit matrix completion without privacy protection, our proposed mechanisms can maintain high-level privacy protection with marginal loss of completion accuracy.
相關內容
In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic noise to the GNN's aggregation function to statistically obfuscate the presence of a single edge (edge-level privacy) or a single node and all its adjacent edges (node-level privacy). Tailored to the specifics of private learning, GAP's new architecture is composed of three separate modules: (i) the encoder module, where we learn private node embeddings without relying on the edge information; (ii) the aggregation module, where we compute noisy aggregated node embeddings based on the graph structure; and (iii) the classification module, where we train a neural network on the private aggregations for node classification without further querying the graph edges. GAP's major advantage over previous approaches is that it can benefit from multi-hop neighborhood aggregations, and guarantees both edge-level and node-level DP not only for training, but also at inference with no additional costs beyond the training's privacy budget. We analyze GAP's formal privacy guarantees using R\'enyi DP and conduct empirical experiments over three real-world graph datasets. We demonstrate that GAP offers significantly better accuracy-privacy trade-offs than state-of-the-art DP-GNN approaches and naive MLP-based baselines.
An interactive mechanism is an algorithm that stores a data set and answers adaptively chosen queries to it. The mechanism is called differentially private, if any adversary cannot distinguish whether a specific individual is in the data set by interacting with the mechanism. We study composition properties of differential privacy in concurrent compositions. In this setting, an adversary interacts with k interactive mechanisms in parallel and can interleave its queries to the mechanisms arbitrarily. Previously, [Vadhan and Wang, TCC 2021] proved an optimal concurrent composition theorem for pure-differential privacy. We significantly generalize and extend their results. Namely, we prove optimal parallel composition properties for several major notions of differential privacy in the literature, including approximate DP, R\'enyi DP, and zero-concentrated DP. Our results demonstrate that the adversary gains no advantage by interleaving its queries to independently running mechanisms. Hence, interactivity is a feature that differential privacy grants us for free.
Face recognition technology has been used in many fields due to its high recognition accuracy, including the face unlocking of mobile devices, community access control systems, and city surveillance. As the current high accuracy is guaranteed by very deep network structures, facial images often need to be transmitted to third-party servers with high computational power for inference. However, facial images visually reveal the user's identity information. In this process, both untrusted service providers and malicious users can significantly increase the risk of a personal privacy breach. Current privacy-preserving approaches to face recognition are often accompanied by many side effects, such as a significant increase in inference time or a noticeable decrease in recognition accuracy. This paper proposes a privacy-preserving face recognition method using differential privacy in the frequency domain. Due to the utilization of differential privacy, it offers a guarantee of privacy in theory. Meanwhile, the loss of accuracy is very slight. This method first converts the original image to the frequency domain and removes the direct component termed DC. Then a privacy budget allocation method can be learned based on the loss of the back-end face recognition network within the differential privacy framework. Finally, it adds the corresponding noise to the frequency domain features. Our method performs very well with several classical face recognition test sets according to the extensive experiments.
Alongside the rapid development of data collection and analysis techniques in recent years, there is increasingly an emphasis on the need to address information leakage associated with such usage of data. To this end, much work in the privacy literature is devoted to the protection of individual users and contributors of data. However, some situations instead require a different notion of data confidentiality involving global properties aggregated over the records of a dataset. Such notions of information protection are particularly applicable for business and organization data, where global properties may reflect trade secrets, or demographic data, which can be harmful if mishandled. Recent work on property inference attacks furthermore shows how data analysis algorithms can be susceptible to leaking these global properties of data, highlighting the importance of developing mechanisms that can protect such information. In this work, we demonstrate how a distribution privacy framework can be applied to formalize the problem of protecting global properties of datasets. Given this framework, we investigate several mechanisms and their tradeoffs for providing this notion of data confidentiality. We analyze the theoretical protection guarantees offered by these mechanisms under various data assumptions, then implement and empirically evaluate these mechanisms for several data analysis tasks. The results of our experiments show that our mechanisms can indeed reduce the effectiveness of practical property inference attacks while providing utility substantially greater than a crude group differential privacy baseline. Our work thus provides groundwork for theoretically supported mechanisms for protecting global properties of datasets.
With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with differential privacy guarantees. However, applying classical differential privacy to language models leads to poor model performance as the underlying privacy notion is over-pessimistic and provides undifferentiated protection for all tokens in the data. Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility. To realize such a new notion, we develop a corresponding privacy mechanism, Selective-DPSGD, for RNN-based language models. Besides language modeling, we also apply the method to a more concrete application--dialog systems. Experiments on both language modeling and dialog system building show that the proposed privacy-preserving mechanism achieves better utilities while remaining safe under various privacy attacks compared to the baselines. The data and code are released at //github.com/wyshi/lm_privacy to facilitate future research .
Large-scale machine learning systems often involve data distributed across a collection of users. Federated learning algorithms leverage this structure by communicating model updates to a central server, rather than entire datasets. In this paper, we study stochastic optimization algorithms for a personalized federated learning setting involving local and global models subject to user-level (joint) differential privacy. While learning a private global model induces a cost of privacy, local learning is perfectly private. We provide generalization guarantees showing that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.
Guaranteeing privacy in released data is an important goal for data-producing agencies. There has been extensive research on developing suitable privacy mechanisms in recent years. Particularly notable is the idea of noise addition with the guarantee of differential privacy. There are, however, concerns about compromising data utility when very stringent privacy mechanisms are applied. Such compromises can be quite stark in correlated data, such as time series data. Adding white noise to a stochastic process may significantly change the correlation structure, a facet of the process that is essential to optimal prediction. We propose the use of all-pass filtering as a privacy mechanism for regularly sampled time series data, showing that this procedure preserves utility while also providing sufficient privacy guarantees to entity-level time series.
Graph-based procedural materials are ubiquitous in content production industries. Procedural models allow the creation of photorealistic materials with parametric control for flexible editing of appearance. However, designing a specific material is a time-consuming process in terms of building a model and fine-tuning parameters. Previous work [Hu et al. 2022; Shi et al. 2020] introduced material graph optimization frameworks for matching target material samples. However, these previous methods were limited to optimizing differentiable functions in the graphs. In this paper, we propose a fully differentiable framework which enables end-to-end gradient based optimization of material graphs, even if some functions of the graph are non-differentiable. We leverage the Differentiable Proxy, a differentiable approximator of a non-differentiable black-box function. We use our framework to match structure and appearance of an output material to a target material, through a multi-stage differentiable optimization. Differentiable Proxies offer a more general optimization solution to material appearance matching than previous work.
Complex networks are graphs representing real-life systems that exhibit unique characteristics not found in purely regular or completely random graphs. The study of such systems is vital but challenging due to the complexity of the underlying processes. This task has nevertheless been made easier in recent decades thanks to the availability of large amounts of networked data. Link prediction in complex networks aims to estimate the likelihood that a link between two nodes is missing from the network. Links can be missing due to imperfections in data collection or simply because they are yet to appear. Discovering new relationships between entities in networked data has attracted researchers' attention in various domains such as sociology, computer science, physics, and biology. Most existing research focuses on link prediction in undirected complex networks. However, not all real-life systems can be faithfully represented as undirected networks. This simplifying assumption is often made when using link prediction algorithms but inevitably leads to loss of information about relations among nodes and degradation in prediction performance. This paper introduces a link prediction method designed explicitly for directed networks. It is based on the similarity-popularity paradigm, which has recently proven successful in undirected networks. The presented algorithms handle the asymmetry in node relationships by modeling it as asymmetry in similarity and popularity. Given the observed network topology, the algorithms approximate the hidden similarities as shortest path distances using edge weights that capture and factor out the links' asymmetry and nodes' popularity. The proposed approach is evaluated on real-life networks, and the experimental results demonstrate its effectiveness in predicting missing links across a broad spectrum of networked data types and sizes.
Increasing privacy concerns have given rise to Private Inference (PI). In PI, both the client's personal data and the service provider's trained model are kept confidential. State-of-the-art PI protocols combine several cryptographic primitives: Homomorphic Encryption (HE), Secret Sharing (SS), Garbled Circuits (GC), and Oblivious Transfer (OT). Today, PI remains largely arcane and too slow for practical use, despite the need and recent performance improvements. This paper addresses PI's shortcomings with a detailed characterization of a standard high-performance protocol to build foundational knowledge and intuition in the systems community. The characterization pinpoints all sources of inefficiency -- compute, communication, and storage. A notable aspect of this work is the use of inference request arrival rates rather than studying individual inferences in isolation. Prior to this work, and without considering arrival rate, it has been assumed that PI pre-computations can be handled offline and their overheads ignored. We show this is not the case. The offline costs in PI are so high that they are often incurred online, as there is insufficient downtime to hide pre-compute latency. We further propose three optimizations to address the computation (layer-parallel HE), communication (wireless slot allocation), and storage (Client-Garbler) overheads leveraging insights from our characterization. Compared to the state-of-the-art PI protocol, the optimizations provide a total PI speedup of 1.8$\times$, with the ability to sustain inference requests up to a 2.24$\times$ greater rate.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191