Android | EPFL Graph Search

Android ( , en français : ) est un système d'exploitation mobile fondé sur le noyau Linux et développé par des informaticiens sponsorisés par Google. À la suite du rachat par Google en 2005 de la startup du même nom, le système avait d'abord été lancé en juin 2007 pour les smartphones et tablettes tactiles, avant de se diversifier dans les objets connectés, ordinateurs comme les télévisions (Android TV), les voitures (Android Auto), les Chromebook (Chrome OS qui utilise les applications Android) et les smartwatch (Wear OS). En 2015, Android est le système d'exploitation mobile le plus utilisé dans le monde, devant iOS d’Apple, avec plus de 80 % de parts de marché dans les smartphones pour l'ensemble de ses versions et adaptations. Caractéristiques Description Dans le Guide du développeur, Android est défini comme étant une pile de logiciels, c'est-à-dire un ensemble de logiciels destinés à fournir une solution clé en main pour les appareils mobiles – smartphone

Privacy-Enhancing Technologies for Mobile Applications and Services

Thi Van Anh Pham

Over a third of the world's population owns a smartphone. As generic computing devices that support a large and heterogeneous collection of mobile applications (apps), smartphones provide a plethora of functionalities and services to billions of users. But the use of these mobile apps and services often introduces privacy risks for users. First, app developers often fail to take into account the fact that as smartphones are generic computing devices, they do not provide adequate privacy and security guarantees for certain types of apps (e.g., those that collect and process sensitive data). As a result, new security and privacy threats are introduced by such apps. Second, due to the lack of privacy by design, apps often over-collect information about users, and can misuse the collected data. Our goal in this thesis is to identify privacy risks in mobile apps and services, and to design privacy-enhancing technologies to mitigate the identified threats. To broaden the impact of our research efforts, we focus on popular apps and services that are currently used by millions of users, and potentially by billions in the future. These include three use-cases: (mobile-health) mHealth apps, ride-hailing services, and activity-tracking services. First, in the case of mHealth apps, we find that the Android operating system allows apps to easily fingerprint and identify other apps installed on the same phone. This causes privacy problems for mHealth apps, because the presence of an mHealth app can already reveal the medical conditions of its users. We investigate the apps' ability to fingerprint other apps and present HideMyApp, a practical system for hiding the presence of sensitive apps on Android. HideMyApp works on stock Android, and no firmware modification or root privilege is required. Second, in ride-hailing services (e.g., Uber), to use the services, riders have to share their pick-up and drop-off locations with service providers. Consequently, the service providers can infer sensitive information about riders' activities (e.g., their visits to health clinics). Therefore, we propose ORide, a privacy-preserving ride-hailing service that efficiently supports the anonymous matching of riders and drivers. Also, ORide still supports functionalities that are often considered as important as privacy, including accountability, payment and reputation-rating operations. Third, in activity-tracking services (e.g., RunKeeper), users report their location-based activities to service providers and obtain rewards based on their performance. However, from the location traces, the service providers can infer sensitive information about the users, e.g., their home/work addresses. Also, to obtain better rewards, the users might try to falsely report their activities to the service providers. Therefore, we propose SecureRun, a solution that enables service providers to compute accurate activity summaries of the users, while guaranteeing the users' location privacy vis-a-vis the service providers. In short, in this thesis, we identify privacy risks in popular mobile apps and services. We show that it is possible to provide them with added privacy, while preserving their rich functionality and usability. We are confident that the contributions presented in this thesis will inspire more future work on protecting users' privacy, not only in the context of mobile apps and services, but also in many other contexts brought about by new technological advances.

EPFL2019

Scale-Out Processors

Pejman Lotfi Kamran

Global-scale online services, such as Google’s Web search and Facebook’s social networking, run in large-scale datacenters. Due to their massive scale, these services are designed to scale out (or distribute) their respective loads and datasets across thousands of servers in datacenters. The growing demand for online services forced service providers to build networks of datacenters, which require an enormous capital outlay for infrastructure, hardware, and power consumption. Consequently, efficiency has become a major concern in the design and operation of such datacenters, with processor efficiency being of, utmost importance, due to the significant contribution of processors to the overall datacenter performance and cost. Scale-out workloads, which are behind today’s online services, serve independent requests, and have large instruction footprints and little data locality. As such, they benefit from processor designs that feature many cores and a modestly sized Last-Level Cache (LLC), a fast access path to the LLC, and high-bandwidth interfaces to memory. Existing server-class processors with large LLCs and a handful of aggressive out-of-order cores are inefficient in executing scale-out workloads. Moreover, the scaling trajectory for these processors leads to even lower efficiency in future technology nodes. This thesis presents a family of throughput-optimal processors, called Scale-Out Processors, for the efficient execution of scale-out workloads. A unique feature of Scale-Out Processors is that they consist of multiple stand-alone modules, called pods, wherein each module is a server running an operating system and a full software stack. To design a throughput-optimal processor, we developed a methodology based on performance density, defined as throughput per unit area, to quantify how effectively an architecture uses the silicon real estate. The proposed methodology derives a performance-density optimal processor building block (i.e., pod), which tightly couples a number of cores to a small LLC via a fast interconnect. Scale-Out Processors simply consist of multiple pods with no inter-pod connectivity or coherence. Moreover, they deliver the highest throughput in today’s technology and afford near-ideal scalability as process technology advances. We demonstrate that Scale-Out Processors improve datacenters’ efficiency by 4.4x-7.1x over datacenters designed using existing server-class processors.

EPFL2013

Advancing the State of Network Switch ASIC Offloading in the Linux Kernel

Andy Roulin

Modern data-center network operating systems rely on proprietary user-space daemons wrapping SDKs from switch vendors. Linux-based variants of these operating systems have benefited from increasing and simplified dataplane offloading support in recent years: kernel resources such as routes and next hops are offloaded to hardware and the kernel can, e.g., learn new MAC entries seen from the hardware forwarding plane. However, the Linux kernel in these operating systems has to be extended and customized as it still lacks constructs (constructs exposed to user-space or in-kernel constructs) needed for complete control plane processing and dataplane offloading. Managing limited hardware resources and keeping the kernel and hardware forwarding planes equivalent are two examples of challenges where the lack of appropriate constructs forces switch operating systems to use user-space solutions coupled with proprietary SDKs and custom kernel modifications. Filling the gaps, i.e., designing and adding the missing constructs, would enable faster control plane processing (less user-kernel context switches) and faster dataplane configura- tion. It would also encourage in-tree kernel drivers from hardware vendors instead of the current closed-source user-space SDKs which would also improve performance while estab- lishing Linux as the standardized API for network switches. This thesis explores the different designs, performance challenges and trade-offs of completing the in-kernel switching API, starting from switch port configuration, faster control path packet processing and ending with in-kernel ASIC resource management. As most hardware vendors are not yet ready to open their drivers in the kernel, workarounds to still provide support for vendors’ SDKs through the same in-kernel API are presented as well. A user-space switch port driver for Mellanox switches was ported to kernel space in order to accelerate control plane processing and bootstrap the in-kernel switch port configuration design. A prefetching scheme which hides PCI latency was designed to manage limited and shared ASIC resources with synchronous feedback to user-space daemons in case of exhausted resources.

2018