The term ‘‘Internet-of-Things’’ is used as an umbrella keyword for covering various aspects related to the extension of the Internet and the Web into the physical realm, by means of the widespread deployment of spatially distributed devices with embedded identification, sensing and/or actuation capabilities. Internet-of-Things envisions a future in which digital and physical entities can be linked, by means of appropriate information and communication technologies, to enable a whole new class of applications and services. In this article, we present a survey of technologies, applications and research challenges for Internetof-Things.

/pdf/internet-of-things-vision-applications-and-research-4xfstaiv80.pdf

Internet of things: Vision, applications and research challenges

We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and active adversary settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73 x communication expansion for 210 users and 220-dimensional vectors, and 1.98 x expansion for 214 users and 224-dimensional vectors over sending data in the clear.

https://dl.acm.org/doi/pdf/10.1145/3133956.3133982

Practical Secure Aggregation for Privacy-Preserving Machine Learning

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Advances and Open Problems in Federated Learning

Internet of Things (IoT) is playing a more and more important role after its showing up, it covers from traditional equipment to general household objects such as WSNs and RFID. With the great potential of IoT, there come all kinds of challenges. This paper focuses on the security problems among all other challenges. As IoT is built on the basis of the Internet, security problems of the Internet will also show up in IoT. And as IoT contains three layers: perception layer, transportation layer and application layer, this paper will analyze the security problems of each layer separately and try to find new problems and solutions. This paper also analyzes the cross-layer heterogeneous integration issues and security issues in detail and discusses the security issues of IoT as a whole and tries to find solutions to them. In the end, this paper compares security issues between IoT and traditional network, and discusses opening security issues of IoT.

https://csi.dgist.ac.kr/uploads/Seminar/1407_IoT_SSH.pdf

Security of the Internet of Things: perspectives and challenges

A seamless solution transparently addresses the characteristics of nomadic systems, and enables existing network applications to run reliably in mobile environments. The solution extends the enterprise network, letting network managers provide mobile users with easy access to the same applications as stationary users without sacrificing reliability or centralized management. The solution combines advantages of existing wire-line network standards with emerging mobile standards to create a solution that works with existing network applications. A Mobility Management Server coupled to the mobile network maintains the state of each of any number of Mobile End Systems and handles the complex session management required to maintain persistent connections to the network and to other peer processes. If a Mobile End System becomes unreachable, suspends, or changes network address (e.g., due to roaming from one network interconnect to another), the Mobility Management Server maintains the connection to the associated peer task—allowing the Mobile End System to maintain a continuous connection even though it may temporarily lose contact with its network medium. In one example, Mobility Management Server communicates with Mobile End Systems using Remote Procedure Call and Internet Mobility Protocols.

Method and apparatus for providing mobile and other intermittent connectivity in a computing environment

A multicast communication source often needs to securely verify which multicast group members have received a message, but verification of individually signed acknowledgments from each member would impose a significant computation and communication cost. As pointed out by Nicolosi and Mazieres [NM04], such cost is minimized if the intermediate nodes along the multicast distribution tree aggregate the individual signatures generated by the multicast receivers into a single multisignature. 
 
While the solution of [NM04], based on a multisignature scheme of Boldyreva [Bol03], relied on so-called “Gap Diffie-Hellman” groups, we propose a solution using a multisignature scheme which is secure under just the discrete logarithm assumption. However, unlike the previously known discrete-log based multisignature scheme of Micali et al. [MOR01a], our multisignature scheme is robust, which allows for an efficient multisignature generation even in the presence of (possibly malicious) node and communication failures.

A Robust Multisignatures Scheme with Applications to Acknowledgment Aggregation.

We present the results of the first large-scale study of the uniqueness of Web browsing histories, gathered from a total of 368,284 Internet users who visited a history detection demonstration website. Our results show that for a majority of users (69 %), the browsing history is unique and that users for whom we could detect at least four visited websites were uniquely identified by their histories in 97 % of cases. We observe a significant rate of stability in browser history fingerprints: for repeat visitors, 38 % of fingerprints are identical over time, and differing ones were correlated with original history contents, indicating static browsing preferences (for history subvectors of size 50). We report a striking result that it is enough to test for a small number of pages in order to both enumerate users’ interests and perform an efficient and unique behavioral fingerprint; we show that testing 50 Web pages is enough to fingerprint 42 % of users in our database, increasing to 70 % with 500 Web pages.

/pdf/on-the-uniqueness-of-web-browsing-history-patterns-5fx9q04xwm.pdf

On the uniqueness of Web browsing history patterns

The lack of flexibility and performance of current communication subsystems has led researchers to look for new protocol architectures. A new design philosophy, flexible and efficient, referred to in the literature as "function-based communication model" is emerging and seems to be very promising. It consists of designing application-tailored communication subsystems adapted to the specific requirements of a given application. The flexibility of such a solution leads to very efficient implementations integrating only required functionalities.

In this paper, we propose a flexible model which uses a synchronous language to synthesize communication subsystems from functional building blocks. We prove the feasibility of our approach by implementing a data transfer protocol using Esterel, a synchronous language. Communication subsystem specifications in our model are very modular; they are composed of parallel modules, implementing the di erent functionalities of the communication subsystem, which synchronize and communicate using signals. The Esterel compiler generates from this parallel specification a sequential automaton by resolving resource conflicts. The design flexibility of our approach is demonstrated; modules are selected according the application requirements and compiled to generate an integrated implementation.

Modular communication subsystem implementation using a synchronous approach

Federated Learning allows distributed entities to train a common model collaboratively without sharing their own data. Although it prevents data collection and aggregation by exchanging only parameter updates, it remains vulnerable to various inference and reconstruction attacks where a malicious entity can learn private information about the participants' training data from the captured gradients. Differential Privacy is used to obtain theoretically sound privacy guarantees against such inference attacks by noising the exchanged update vectors. However, the added noise is proportional to the model size which can be very large with modern neural networks. This can result in poor model quality. In this paper, compressive sensing is used to reduce the model size and hence increase model quality without sacrificing privacy. We show experimentally, using 2 datasets, that our privacy-preserving proposal can reduce the communication costs by up to 95% with only a negligible performance penalty compared to traditional non-private federated learning schemes.

Compression Boosts Differentially Private Federated Learning

Although they address the same problem, the so-called “centralized” and “decentralized” approaches to COVID-19 proximity tracing rely on different threat model assumptions. The goal of this document is to analyze the impact of these two options in terms of privacy, security and reliability.

The main objective of the decentralized approach is to protect users against a malicious server or a state-level adversary and to prevent the leak of sensitive data due to attacks or negligence at the server side. Therefore, the role of the server is reduced as much as possible, and the exposure verification is performed on the user device. In contrast, the centralized approach puts more emphasis on the protection of users against other malicious users trying to infer who is infected. Hence, the role of the server in the centralized approach is more important, including the verification of exposure.

This design choice involves different privacy risks:
● The decentralized approach provides many opportunities to malicious or curious users (through wide scale and undetectable attacks or during normal usage) to infer the identity of infected users or to monitor specific areas. These privacy risks coming from users (e.g., neighbors) can easily lead to abuses as well as stigmatization and harassment of diagnosed users. On the positive side, the server learns little information about users.
● In the centralized approach, in contrast, the capability of users to learn who is infected is drastically limited. This better protection however comes at the cost of relying on a server which is able to learn some information about users.

Law enforcement agencies and third parties colluding with the server are sources of risk in both approaches but they do not concern the same population. Only infected users who consent to declare themselves are concerned in the decentralized approach, while these risks concern all users (infected or not) in the centralized approach. However, the likelihood of these risks needs to be assessed and balanced, as all other risks, with the potential benefits of these applications in the fight against COVID-19. To this respect, the centralized approach can bring added value because the health authority is aware of the number of exposed people and can use it both for statistical purposes and to easily adjust the risk calculation algorithm (to decide if a user should be classified as “at risk”).

https://hal.inria.fr/hal-02570676/document

Claude Castelluccia

Papers

A Robust Multisignatures Scheme with Applications to Acknowledgment Aggregation.

On the uniqueness of Web browsing history patterns

Modular communication subsystem implementation using a synchronous approach

Compression Boosts Differentially Private Federated Learning

Proximity Tracing Approaches - Comparative Impact Analysis