اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدOn the Convergence of Deep Learning with Differential Privacy
105
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In deep learning with differential privacy (DP), the neural network achieves the privacy usually at the cost of slower convergence (and thus lower performance) than its non-private counterpart. This work gives the first convergence analysis of the DP deep learning, through the lens of training dynamics and the neural tangent kernel (NTK). Our convergence theory successfully characterizes the effects of two key components in the DP training: the per-sample clipping (flat or layerwise) and the noise addition. Our analysis not only initiates a general principled framework to understand the DP deep learning with any network architecture and loss function, but also motivates a new clipping method -- the global clipping, that significantly improves the convergence while preserving the same privacy guarantee as the existing local clipping. In terms of theoretical results, we establish the precise connection between the per-sample clipping and NTK matrix. We show that in the gradient flow, i.e., with infinitesimal learning rate, the noise level of DP optimizers does not affect the convergence. We prove that DP gradient descent (GD) with global clipping guarantees the monotone convergence to zero loss, which can be violated by the existing DP-GD with local clipping. Notably, our analysis framework easily extends to other optimizers, e.g., DP-Adam. Empirically speaking, DP optimizers equipped with global clipping perform strongly on a wide range of classification and regression tasks. In particular, our global clipping is surprisingly effective at learning calibrated classifiers, in contrast to the existing DP classifiers which are oftentimes over-confident and unreliable. Implementation-wise, the new clipping can be realized by adding one line of code into the Opacus library.
قيم البحث
اقرأ أيضاً
Deep learning models are often trained on datasets that contain sensitive information such as individuals shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural netwo
rks subject to privacy constraints that are specified by differential privacy or its divergence-based relaxations. These privacy definitions, however, have weaknesses in handling certain important primitives (composition and subsampling), thereby giving loose or complicated privacy analyses of training neural networks. In this paper, we consider a recently proposed privacy definition termed textit{$f$-differential privacy} [18] for a refined privacy analysis of training neural networks. Leveraging the appealing properties of $f$-differential privacy in handling composition and subsampling, this paper derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as [3] did. Our results demonstrate that the $f$-differential privacy framework allows for a new privacy analysis that improves on the prior analysis~[3], which in turn suggests tuning certain parameters of neural networks for a better prediction accuracy without violating the privacy budget. These theoretically derived improvements are confirmed by our experiments in a range of tasks in image classification, text classification, and recommender systems. Python code to calculate the privacy cost for these experiments is publicly available in the texttt{TensorFlow Privacy} library.
Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the explanation d
ata used to generate them, thus undermining data privacy. To address this issue, we propose differentially private algorithms to construct feature-based model explanations. We design an adaptive differentially private gradient descent algorithm, that finds the minimal privacy budget required to produce accurate explanations. It reduces the overall privacy loss on explanation data, by adaptively reusing past differentially private explanations. It also amplifies the privacy guarantees with respect to the training data. We evaluate the implications of differentially private models and our privacy mechanisms on the quality of model explanations.
The collection and sharing of individuals data has become commonplace in many industries. Local differential privacy (LDP) is a rigorous approach to preserving data privacy even from a database administrator, unlike the more standard central differen
tial privacy. To achieve LDP, one traditionally adds noise directly to each data dimension, but for high-dimensional data the level of noise required for sufficient anonymization all but entirely destroys the datas utility. In this paper, we introduce a novel LDP mechanism that leverages representation learning to overcome the prohibitive noise requirements of direct methods. We demonstrate that, rather than simply estimating aggregate statistics of the privatized data as is the norm in LDP applications, our method enables the training of performant machine learning models. Unique applications of our approach include private novel-class classification and the augmentation of clean datasets with additional privatized features. Methods that rely on central differential privacy are not applicable to such tasks. Our approach achieves significant performance gains on these tasks relative to state-of-the-art LDP benchmarks that noise data directly.
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds.
We adapt the Bayesian privacy accounting method to the federated setting and suggest multiple improvements for more efficient privacy budgeting at different levels. Our experiments show significant advantage over the state-of-the-art differential privacy bounds for federated learning on image classification tasks, including a medical application, bringing the privacy budget below 1 at the client level, and below 0.1 at the instance level. Lower amounts of noise also benefit the model accuracy and reduce the number of communication rounds.
Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and identitie
s from face dataset. However, most of these studies focus on supervised learning models. As deep reinforcement learning (DRL) has been deployed in a number of real-world systems, such as indoor robot navigation, whether trained DRL policies can leak private information requires in-depth study. To explore such privacy breaches in general, we mainly propose two methods: environment dynamics search via genetic algorithm and candidate inference based on shadow policies. We conduct extensive experiments to demonstrate such privacy vulnerabilities in DRL under various settings. We leverage the proposed algorithms to infer floor plans from some trained Grid World navigation DRL agents with LiDAR perception. The proposed algorithm can correctly infer most of the floor plans and reaches an average recovery rate of 95.83% using policy gradient trained agents. In addition, we are able to recover the robot configuration in continuous control environments and an autonomous driving simulator with high accuracy. To the best of our knowledge, this is the first work to investigate privacy leakage in DRL settings and we show that DRL-based agents do potentially leak privacy-sensitive information from the trained policies.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
