Accounting for privacy loss under fully adaptive composition -- where mechanism choice and privacy parameters may depend on the history of prior outputs -- is a central challenge in differential privacy (DP). Here, privacy filters are stopping rules ensuring a prescribed global budget is not exceeded. A leading candidate for optimal filter design is $f$-DP, which characterizes the full extent of adversarial hypothesis testing and recovers $(\varepsilon,δ)$-DP through piece-wise linear trade-off functions, while enabling tight $(\varepsilon,δ)$-DP accounting in standard compositions via tensor products. Yet whether such filters can be correctly defined under $f$-DP remains unclear. We show that the natural $f$-DP filter -- tracking path-wise accumulating tensor products and stopping when the prescribed curve is crossed -- is fundamentally invalid, precluding the direct use of standard efficient numerical Fast-Fourier-Transform accounting in the fully adaptive setting. We characterize this failure, establishing necessary and sufficient conditions for the natural filter's validity. Furthermore, we prove a fully adaptive central limit theorem for $f$-DP, establishing Gaussian convergence of cumulative privacy losses under full adaptivity. As a demonstration, we construct a closed-form approximate GDP filter for subsampled Gaussian mechanisms that provably outperforms RDP-based accounting in asymptotic regimes ($q\ll 1$ and $q\approx 1$) without tracking the full trade-off function, demonstrating that the slack in RDP is not intrinsic to adaptive composition -- though CLT-based approximations are known to be optimistic at realistic subsampling rates, a limitation that remains an open challenge.
DPBloomfilter: Securing Bloom Filters with Differential Privacy
Independent Researcher（独立研究者）；The University of Hong Kong（香港大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
In this paper we initiate the study of adaptive composition in differential privacy when the length of the composition, and the privacy parameters themselves can be chosen adaptively, as a function of the outcome of previously run analyses. This case is much more delicate than the setting covered by existing composition theorems, in which the algorithms themselves can be chosen adaptively, but the privacy parameters must be fixed up front. Indeed, it isn't even clear how to define differential privacy in the adaptive parameter setting. We proceed by defining two objects which cover the two mai…
Internet Users' Information Privacy Concerns (IUIPC-10) is one of the most endorsed privacy concern scales. It is widely used in the evaluation of human factors of PETs and the investigation of the privacy paradox. Even though its predecessor Concern For Information Privacy (CFIP) has been evaluated independently and the instrument itself seen some scrutiny, we are still missing a dedicated confirmation of IUIPC-10, itself. We aim at closing this gap by systematically analyzing IUIPC's construct validity and reliability. We obtained three mutually independent samples with a total of $N = 1031$…
The popularity and projected growth of in-home smart speaker assistants, such as Amazon's Echo, has raised privacy concerns among consumers and privacy advocates. Notable questions regarding the collection and storage of user data by for-profit organizations include: what data is being collected and how is it being used, who has or can obtain access to such data, and how can user privacy be maintained while providing useful services. In addition to concerns regarding what the speaker manufacturer will do with your data, there are also more fundamental concerns about the security of these devic…
A core problem in the development and maintenance of crowd-sourced filter lists is that their maintainers cannot confidently predict whether (and where) a new filter list rule will break websites. This is a result of enormity of the Web, which prevents filter list authors from broadly understanding the impact of a new blocking rule before they ship it to millions of users. The inability of filter list authors to evaluate the Web compatibility impact of a new rule before shipping it severely reduces the benefits of filter-list-based content blocking: filter lists are both overly-conservative (i…
Apple（苹果公司）；University of California, Berkeley（加利福尼亚大学伯克利分校）
We consider a sequential setting in which a single dataset of individuals is used to perform adaptively-chosen analyses, while ensuring that the differential privacy loss of each participant does not exceed a pre-specified privacy budget. The standard approach to this problem relies on bounding a worst-case estimate of the privacy loss over all individuals and all possible values of their data, for every single analysis. Yet, in many scenarios this approach is overly conservative, especially for "typical" data points which incur little privacy loss by participation in most of the analyses. In …
With the ubiquitous advancement in smart medical devices and systems, the potential of Remote Patient Monitoring (RPM) network is evolving in modern healthcare systems. The medical professionals (doctors, nurses, or medical experts) can access vitals and sensitive physiological information about the patients and provide proper treatment to improve the quality of life through the RPM network. However, the wireless nature of communication in the RPM network makes it challenging to design an efficient mechanism for secure communication. Many authentication schemes have been proposed in recent yea…
We study the security of Probabilistic Data Structures (PDS) for handling Approximate Membership Queries (AMQ); prominent examples of AMQ-PDS are Bloom and Cuckoo filters. AMQ-PDS are increasingly being deployed in environments where adversaries can gain benefit from carefully selecting inputs, for example to increase the false positive rate of an AMQ-PDS. They are also being used in settings where the inputs are sensitive and should remain private in the face of adversaries who can access an AMQ-PDS through an API or who can learn its internal state by compromising the system running the AMQ-…
This paper proposes a new recommendation system preserving both privacy and utility. It relies on the local differential privacy (LDP) for the browsing user to transmit his noisy preference profile, as perturbed Bloom filters, to the service provider. The originality of the approach is multifold. First, as far as we know, the approach is the first one including at the user side two perturbation rounds - PRR (Permanent Randomized Response) and IRR (Instantaneous Randomized Response) - over a complete user profile. Second, a full validation experimentation chain is set up, with a machine learnin…
Beijing Jiaotong University（北京交通大学）；Peng Cheng Laboratory（鹏城实验室）；Beijing University of Technology（北京工业大学）；Beijing Artificial Intelligence Institute（北京人工智能研究院）
While widely adopted in practical applications, face recognition has been critically discussed regarding the malicious use of face images and the potential privacy problems, e.g., deceiving payment system and causing personal sabotage. Online photo sharing services unintentionally act as the main repository for malicious crawler and face recognition applications. This work aims to develop a privacy-preserving solution, called Adversarial Privacy-preserving Filter (APF), to protect the online shared face images from being maliciously used.We propose an end-cloud collaborated adversarial attack …
Etsy Inc（Etsy公司）；Rutgers University（罗格斯大学）；University at Albany, SUNY（纽约州立大学奥尔巴尼分校）
Recently, there has been an increasing adoption of differential privacy guided algorithms for privacy-preserving machine learning tasks. However, the use of such algorithms comes with trade-offs in terms of algorithmic fairness, which has been widely acknowledged. Specifically, we have empirically observed that the classical collaborative filtering method, trained by differentially private stochastic gradient descent (DP-SGD), results in a disparate impact on user groups with respect to different user engagement levels. This, in turn, causes the original unfair model to become even more biased…
Content blocking is an important part of a performant, user-serving, privacy respecting web. Most content blockers build trust labels over URLs. While useful, this approach has well understood shortcomings. Attackers may avoid detection by changing URLs or domains, bundling unwanted code with benign code, or inlining code in pages. The common flaw in existing approaches is that they evaluate code based on its delivery mechanism, not its behavior. In this work we address this problem with a system for generating signatures of the privacy-and-security relevant behavior of executed JavaScript. Ou…
In this work, we introduce a new approach for statistical quantification of differential privacy in a black box setting. We present estimators and confidence intervals for the optimal privacy parameter of a randomized algorithm $A$, as well as other key variables (such as the "data-centric privacy level"). Our estimators are based on a local characterization of privacy and in contrast to the related literature avoid the process of "event selection" - a major obstacle to privacy validation. This makes our methods easy to implement and user-friendly. We show fast convergence rates of the estimat…
We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst. Such an analyst selects mechanisms (to be run on a sensitive data set) and their privacy budgets adaptively, that is, based on the answers from other mechanisms run previously on the same data set. In the language of Rogers, Roth, Ullman and Vadhan, this gives a filter for GDP with the same parameters as for nonadaptive composition.
We consider a database $\vec{X} = (X_1,\cdots,X_n)$ containing the data of $n$ users. The data aggregator wants to publicise the database, but wishes to sanitise the dataset to hide sensitive data $S_i$ correlated to $X_i$. This setting is considered in the Privacy Funnel, which uses mutual information as a leakage metric. The downsides to this approach are that mutual information does not give worst-case guarantees, and that finding optimal sanitisation protocols can be computationally prohibitive. We tackle these problems by using differential privacy metrics, and by considering local protoc…
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 o…
In the Open Data approach, governments and other public organisations want to share their datasets with the public, for accountability and to support participation. Data must be opened in such a way that individual privacy is safeguarded. The Privacy Funnel is a mathematical approach that produces a sanitised database that does not leak private data beyond a chosen threshold. The downsides to this approach are that it does not give worst-case privacy guarantees, and that finding optimal sanitisation protocols can be computationally prohibitive. We tackle these problems by using differential pr…
Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data
Computer Engineering Department, İstanbul Commerce University（伊斯坦布尔商业大学计算机工程系）；Turkcell Teknoloji（Turkcell技术公司）；Grid Communications and Security Group, Electrification and Energy Infrastructures Division, Oak Ridge National Laboratory（橡树岭国家实验室电网安全与能源基础设施部门）
针对联邦学习中的噪声标签、类别缺失与不均衡问题，提出结合自适应噪声清洗、条件 GAN 合成补全和鲁棒训练的隐私保护框架，并在 MNIST 与 Fashion-MNIST 上验证其性能提升。
Differential Privacy Mechanisms in Neural Tangent Kernel Regression
Adobe Research（奥多比研究院）；The University of Hong Kong（香港大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Tsinghua University（清华大学）；The Simons Institute for the Theory of Computing at the University of California, Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）
Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the quantity of interest on the underlying population. The cost of this protection is the accuracy loss incurred by differential privacy. In this work, inspired by standard models in the genomics literature, we consider data models in which individuals are represented by a sequence of attributes with the property that where distant attributes are only weakly co…
For evolving datasets with continual reports, the composition rule for differential privacy (DP) dictates that the scale of DP noise must grow linearly with the number of the queries, or that the privacy budget must be split equally between all the queries, so that the privacy budget across all the queries remains bounded and consistent with the privacy guarantees. To avoid this drawback of DP, we consider datasets containing almost periodic time series, composed of periodic components and noisy variations on top that are independent across periods. Our interest in these datasets is motivated …
