Location-based Services (LBSs) provide valuable services, with convenient features for users. However, the information disclosed through each request harms user privacy. This is a concern particularly with honest-but-curious LBS servers, which could, by collecting requests, track users and infer additional sensitive user data. This is the motivation of both centralized and decentralized location privacy protection schemes for LBSs: anonymizing and obfuscating LBS queries to not disclose exact information, while still getting useful responses. Decentralized schemes overcome the disadvantages of centralized schemes, eliminating anonymizers and enhancing users' control over sensitive information. However, an insecure decentralized system could pose even more serious security threats than privacy leakage. We address exactly this problem, by proposing security enhancements for mobile data sharing systems. We protect user privacy while preserving accountability of user activities, leveraging pseudonymous authentication with mainstream cryptography. Our design leverages architectures proposed for large scale mobile systems, while it incurs minimal changes to LBS servers as it can be deployed in parallel to the LBS servers. This further motivates the adoption of our design, in order to cater to the needs of privacy-sensitive users. We provide an analysis of security and privacy concerns and countermeasures, as well as a performance evaluation of basic protocol operations showing the practicality of our design.
Resource Public Key Infrastructure (RPKI) is vital to the security of inter-domain routing. However, RPKI enables Regional Internet Registries (RIRs) to unilaterally takedown IP prefixes - indeed, such attacks have been launched by nation-state adversaries. The threat of IP prefix takedowns is one of the factors hindering RPKI adoption. In this work, we propose the first distributed RPKI system, based on threshold signatures, that requires the coordination of a number of RIRs to make changes to RPKI objects; hence, preventing unilateral prefix takedown. We perform extensive evaluations using o…
Location-Based Services (LBSs) provide valuable services, with convenient features for mobile users. However, the location and other information disclosed through each query to the LBS erodes user privacy. This is a concern especially because LBS providers can be honest-but-curious, collecting queries and tracking users' whereabouts and infer sensitive user data. This motivated both centralized and decentralized location privacy protection schemes for LBSs: anonymizing and obfuscating LBS queries to not disclose exact information, while still getting useful responses. Decentralized schemes ove…
Cloud-edge collaborative inference approach splits deep neural networks (DNNs) into two parts that run collaboratively on resource-constrained edge devices and cloud servers, aiming at minimizing inference latency and protecting data privacy. However, even if the raw input data from edge devices is not directly exposed to the cloud, state-of-the-art attacks targeting collaborative inference are still able to reconstruct the raw private data from the intermediate outputs of the exposed local models, introducing serious privacy risks. In this paper, a secure privacy inference framework for cloud…
With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example, federated learning, to train a shared deep model across multiple participants. It could effectively take advantage of the resources of each participant and obtain a more powerful learning system. However, integrity and privacy threats in such systems have greatly obstructed the applications of collaborative learning. And a large amount of works have been proposed to maintain the model integrity and mitigate the pri…
Collaboration among multiple organizations is imperative for contemporary intrusion detection. As modern threats become well sophisticated it is difficult for organizations to defend with threat context local to their networks alone. Availability of global \emph{threat intelligence} is must for organizations to defend against modern advanced persistent threats (APTs). In order to benefit from such global context of attacks, privacy concerns continue to be of major hindrance. In this position paper we identify real world privacy problems as precise use cases, relevant cryptographic technologies…
Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the cloud. However, the reconstruction attack was proposed recently to recover the original input image from intermediate outputs that can be collected from local models in collaborative inference. For addressing such privacy issues, a promising technique is to adopt differential privacy so that the intermediate outputs are protected with a small accuracy loss. …
Mobile devices with rich features can record videos, traffic parameters or air quality readings along user trajectories. Although such data may be valuable, users are seldom rewarded for collecting them. Emerging digital marketplaces allow owners to advertise their data to interested buyers. We focus on geo-marketplaces, where buyers search data based on geo-tags. Such marketplaces present significant challenges. First, if owners upload data with revealed geo-tags, they expose themselves to serious privacy risks. Second, owners must be accountable for advertised data, and must not be allowed t…
CRSF: Collusion-Resilient Privacy-Preserving Sensor Fusion with Byzantine-Robust Participation
Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Centrum Wiskunde & Informatica（荷兰数学与计算机科学研究学会）；Southwest University（西南大学）；Yangtze Delta Region Institute of Tsinghua University（清华大学长三角研究院）；University of Trento（特伦托大学）
Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct sensitive training data using leaked gradients with high attack success rate. Although deep learning with differential privacy is a defacto standard for publishing deep learning models with differential privacy guarantee, we show that differentially private algorithms with fixed privacy parameters are vulnerable against gradient leakage attacks. This paper inve…
With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, Privacy-Preserving Machine Learning (PPML) has received much attention from both academia and industry. However, organizations are faced with the dilemma that, on the one hand, they are encouraged to share data to enhance ML performance, but on the other hand, they could potentially be breaching the relevant data privacy regulations. Practical PPML typically allows multiple participants to individ…
Spam phone calls have been rapidly growing from nuisance to an increasingly effective scam delivery tool. To counter this increasingly successful attack vector, a number of commercial smartphone apps that promise to block spam phone calls have appeared on app stores, and are now used by hundreds of thousands or even millions of users. However, following a business model similar to some online social network services, these apps often collect call records or other potentially sensitive information from users' phones with little or no formal privacy guarantees. In this paper, we study whether it…
The Internet of Vehicles (IoV) is flourishing and offers various applications relating to road safety, traffic and fuel efficiency, and infotainment. Dealing with security and privacy threats and managing the trust (detecting malicious and misbehaving peers) in IoV remains the most significant concern. Artificial Intelligence is one of the most revolutionizing technologies, and the predictive power of its machine learning models can help detect intrusions and misbehaviors. Similarly, empowering the state-of-the-art IoV security framework with blockchain can make it secure and resilient. This a…
The rogue DHCP is unauthorized server that releases the incorrect IP address to users and sniffs the traffic illegally. The contribution specially provides privacy to users and enhances the security aspects of mobile supported collaborative framework (MSCF) explained in [24].The paper introduces multi-frame signature-cum anomaly-based intrusion detection systems (MSAIDS) supported with novel algorithms and inclusion of new rules in existing IDS. The major target of contribution is to detect the malicious attacks and blocks the illegal activities of rogue DHCP server. This innovative security m…
Georgia Institute of Technology（佐治亚理工学院）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Federated learning(FL) is an emerging distributed learning paradigm with default client privacy because clients can keep sensitive data on their devices and only share local training parameter updates with the federated server. However, recent studies reveal that gradient leakages in FL may compromise the privacy of client training data. This paper presents a gradient leakage resilient approach to privacy-preserving federated learning with per training example-based client differential privacy, coined as Fed-CDP. It makes three original contributions. First, we identify three types of client g…
Collaborative learning enables two or more participants, each with their own training dataset, to collaboratively learn a joint model. It is desirable that the collaboration should not cause the disclosure of either the raw datasets of each individual owner or the local model parameters trained on them. This privacy-preservation requirement has been approached through differential privacy mechanisms, homomorphic encryption (HE) and secure multiparty computation (MPC), but existing attempts may either introduce the loss of model accuracy or imply significant computational and/or communicational…
With the rise of online lenders, the loan stacking problem has become a significant issue in the financial industry. One of the key steps in the fight against it is the querying of the loan history of a borrower from peer lenders. This is especially important in markets without a trusted credit bureau. To protect participants privacy and business interests, we want to hide borrower identities and lenders data from the loan originator, while simultaneously verifying that the borrower authorizes the query. In this paper, we propose Octopus, a distributed system to execute the query while meeting…
Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing dimensionality reduced representations of data has been proposed as a non-model sharing-type federated learning. This paper analyzes the accuracy and privacy evaluations of this novel framework. In the accuracy analysis, we provided sufficient conditions for the equivalence of the collaborative data analysis and the centralized analysis with dimensionality reduction. In the privacy analysis, we proved that collaborat…
Real-time, online-editing web apps provide free and convenient services for collaboratively editing, sharing and storing files. The benefits of these web applications do not come for free: not only do service providers have full access to the users' files, but they also control access, transmission, and storage mechanisms for them. As a result, user data may be at risk of data mining, third-party interception, or even manipulation. To combat this, we propose a new system for helping to preserve the privacy of user data within collaborative environments. There are several distinct challenges in…
The neighbourhood-based Collaborative Filtering is a widely used method in recommender systems. However, the risks of revealing customers' privacy during the process of filtering have attracted noticeable public concern recently. Specifically, $k$NN attack discloses the target user's sensitive information by creating $k$ fake nearest neighbours by non-sensitive information. Among the current solutions against $k$NN attack, the probabilistic methods showed a powerful privacy preserving effect. However, the existing probabilistic methods neither guarantee enough prediction accuracy due to the gl…
In collaborative recommendation systems, privacy may be compromised, as users' opinions are used to generate recommendations for others. In this paper, we consider an online collaborative recommendation system, and we measure users' privacy in terms of the standard differential privacy. We give the first quantitative analysis of the trade-offs between recommendation quality and users' privacy in such a system by showing a lower bound on the best achievable privacy for any non-trivial algorithm, and proposing a near-optimal algorithm. From our results, we find that there is actually little trad…
Laboratory for Data Security -- EPFL（数据安全实验室 -- 洛桑联邦理工学院）
Tree-based models are among the most efficient machine learning techniques for data mining nowadays due to their accuracy, interpretability, and simplicity. The recent orthogonal needs for more data and privacy protection call for collaborative privacy-preserving solutions. In this work, we survey the literature on distributed and privacy-preserving training of tree-based models and we systematize its knowledge based on four axes: the learning algorithm, the collaborative model, the protection mechanism, and the threat model. We use this to identify the strengths and limitations of these works…
Most of the smart applications, such as smart energy metering devices, demand strong privacy preservation to strengthen data privacy. However, it is difficult to protect the privacy of the smart device data, especially on the client side. It is mainly because payment for billing is computed by the server deployed at the client's side, and it is highly challenging to prevent the leakage of client's information to unauthorised users. Various researchers have discussed this problem and have proposed different privacy preservation techniques. Conventional techniques suffer from the problem of high…
Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Department of Statistics, Texas A&M University（德克萨斯农工大学统计系）；Nanchang University（南昌大学）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Hong Kong University of Science and Technology（香港科技大学）
Distributed Hash Tables (DHT) are a common architecture for decentralized applications and, therefore, would be suited for privacy-aware applications. However, currently existing DHTs allow every peer to access any index. To build privacy-aware applications, we need to control this access. In this paper, we present k-rAC, a privacy-aware fine-grained AC for DHTs. For authentication, we present three different mechanisms based on public-key cryptography, zero-knowledge-proofs, and cryptographic hashes. For authorization, we use distributed AC lists. The security of our approach is based on k-re…
Collaborative filtering (CF) recommendation algorithms are well-known for their outstanding recommendation performances, but previous researches showed that they could cause privacy leakage for users due to k-nearest neighboring (KNN) attacks. Recently, the notion of differential privacy (DP) has been applied to privacy preservation for collaborative filtering recommendation algorithms. However, as far as we know, existing differentially private CF recommendation schemes degraded the recommendation performance (such as recall and precision) to an unacceptable level. In this paper, in order to …
Los Andes University（洛斯安第斯大学）；Rappi（Rappi公司）；Amazon（亚马逊）
Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organization must assure that sensitive data remains private throughout the whole ML pipeline, i.e., training and inference phases. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data. Thus, organizations can share the data representation to increase machine learning mo…
Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
The University of Alabama（阿拉巴马大学）；Alabama Center for the Advancement of AI（阿拉巴马人工智能 advancement 中心）；Trustworthy AI Lab（可信人工智能实验室）；Department of Computer Science, The University of Alabama（计算机科学系）
In order to receive personalized services, individuals share their personal data with a wide range of service providers, hoping that their data will remain confidential. Thus, in case of an unauthorized distribution of their personal data by these service providers (or in case of a data breach) data owners want to identify the source of such data leakage. Digital fingerprinting schemes have been developed to embed a hidden and unique fingerprint into shared digital content, especially multimedia, to provide such liability guarantees. However, existing techniques utilize the high redundancy in …
Missouri University of Science and Technology（密苏里科技大学）；University of Missouri-Columbia（密苏里大学哥伦比亚分校）；Applied Computational Intelligence Laboratory, Missouri University of Science and Technology（密苏里科技大学应用计算智能实验室）
Collaborative filtering recommendation systems provide recommendations to users based on their own past preferences, as well as those of other users who share similar interests. The use of recommendation systems has grown widely in recent years, helping people choose which movies to watch, books to read, and items to buy. However, users are often concerned about their privacy when using such systems, and many users are reluctant to provide accurate information to most online services. Privacy-preserving collaborative filtering recommendation systems aim to provide users with accurate recommend…
To date publish of a giant social network jointly from different parties is an easier collaborative approach. Agencies and researchers who collect such social network data often have a compelling interest in allowing others to analyze the data. In many cases the data describes relationships that are private and sharing the data in full can result in unacceptable disclosures. Thus, preserving privacy without revealing sensitive information in the social network is a serious concern. Recent developments for preserving privacy using anonymization techniques are focused on relational data only. Pr…
Machine learning is promising, but it often needs to process vast amounts of sensitive data which raises concerns about privacy. In this white-paper, we introduce Substra, a distributed framework for privacy-preserving, traceable and collaborative Machine Learning. Substra gathers data providers and algorithm designers into a network of nodes that can train models on demand but under advanced permission regimes. To guarantee data privacy, Substra implements distributed learning: the data never leave their nodes; only algorithms, predictive models and non-sensitive metadata are exchanged on the…
When multiple parties that deal with private data aim for a collaborative prediction task such as medical image classification, they are often constrained by data protection regulations and lack of trust among collaborating parties. If done in a privacy-preserving manner, predictive analytics can benefit from the collective prediction capability of multiple parties holding complementary datasets on the same machine learning task. This paper presents PRICURE, a system that combines complementary strengths of secure multi-party computation (SMPC) and differential privacy (DP) to enable privacy-p…
Luxembourg Institute of Science and Technology (LIST)（卢森堡科学技术研究院（LIST））
Collaborative filtering recommenders provide effective personalization services at the cost of sacrificing the privacy of their end users. Due to the increasing concerns from the society and stricter privacy regulations, it is an urgent research challenge to design privacy-preserving and yet robust recommenders which offer recommendation services to privacy-aware users. Our analysis shows that existing solutions fall short in several aspects, including lacking attention to the precise output to end users and ignoring the correlated robustness issues. In this paper, we provide a general system …
With increasing usage of deep learning algorithms in many application, new research questions related to privacy and adversarial attacks are emerging. However, the deep learning algorithm improvement needs more and more data to be shared within research community. Methodologies like federated learning, differential privacy, additive secret sharing provides a way to train machine learning models on edge without moving the data from the edge. However, it is very computationally intensive and prone to adversarial attacks. Therefore, this work introduces a privacy preserving FedCollabNN framework …
Vehicular ad hoc network (VANET) is an enabling technology in modern transportation systems for providing safety and valuable information, and yet vulnerable to a number of attacks from passive eavesdropping to active interfering. Intrusion detection systems (IDSs) are important devices that can mitigate the threats by detecting malicious behaviors. Furthermore, the collaborations among vehicles in VANETs can improve the detection accuracy by communicating their experiences between nodes. To this end, distributed machine learning is a suitable framework for the design of scalable and implement…
Emory University（埃默里大学）；UT Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
Tensor factorization has been demonstrated as an efficient approach for computational phenotyping, where massive electronic health records (EHRs) are converted to concise and meaningful clinical concepts. While distributing the tensor factorization tasks to local sites can avoid direct data sharing, it still requires the exchange of intermediary results which could reveal sensitive patient information. Therefore, the challenge is how to jointly decompose the tensor under rigorous and principled privacy constraints, while still support the model's interpretability. We propose DPFact, a privacy-…
