ترغب بنشر مسار تعليمي؟ اضغط هنا

Privacy and Integrity Preserving Training Using Trusted Hardware

166   0   0.0 ( 0 )
 نشر من قبل Hanieh Hashemi
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However, Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. This work presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides privacy and integrity verification, while accelerators perform the computation heavy linear algebraic operations.



قيم البحث

اقرأ أيضاً

In the digital era, users share their personal data with service providers to obtain some utility, e.g., access to high-quality services. Yet, the induced information flows raise privacy and integrity concerns. Consequently, cautious users may want t o protect their privacy by minimizing the amount of information they disclose to curious service providers. Service providers are interested in verifying the integrity of the users data to improve their services and obtain useful knowledge for their business. In this work, we present a generic solution to the trade-off between privacy, integrity, and utility, by achieving authenticity verification of data that has been encrypted for offloading to service providers. Based on lattice-based homomorphic encryption and commitments, as well as zero-knowledge proofs, our construction enables a service provider to process and reuse third-party signed data in a privacy-friendly manner with integrity guarantees. We evaluate our solution on different use cases such as smart-metering, disease susceptibility, and location-based activity tracking, thus showing its versatility. Our solution achieves broad generality, quantum-resistance, and relaxes some assumptions of state-of-the-art solutions without affecting performance.
The widening availability of hardware-based trusted execution environments (TEEs) has been accelerating the adaptation of new applications using TEEs. Recent studies showed that a cloud application consists of multiple distributed software modules pr ovided by mutually distrustful parties. The applications use multiple TEEs (enclaves) communicating through software-encrypted memory channels. Such execution model requires bi-directional protection: protecting the rest of the system from the enclave module with sandboxing and protecting the enclave module from a third-part module and operating systems. However, the current TEE model, such as Intel SGX, cannot efficiently represent such distributed sandbox applications. To overcome the lack of hardware supports for sandboxed TEEs, this paper proposes an extended enclave model called Stockade, which supports distributed sandboxes hardened by hardware. Stockade proposes new three key techniques. First, it extends the hardware-based memory isolation in SGX to confine a user software module only within its enclave. Second, it proposes a trusted monitor enclave that filters and validates systems calls from enclaves. Finally, it allows hardware-protected memory sharing between a pair of enclaves for efficient protected communication without software-based encryption. Using an emulated SGX platform with the proposed extensions, this paper shows that distributed sandbox applications can be effectively supported with small changes of SGX hardware.
Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the clients data du ring training, and how to ensure integrity of the trained model. We propose a two-pronged solution that aims to address both challenges under a single framework. First, we propose to create secure enclaves using a trusted execution environment (TEE) within the server. Each client can then encrypt their gradients and send them to verifiable enclaves. The gradients are decrypted within the enclave without the fear of privacy breaches. However, robustness check computations in a TEE are computationally prohibitive. Hence, in the second step, we perform a novel gradient encoding that enables TEEs to encode the gradients and then offloading Byzantine check computations to accelerators such as GPUs. Our proposed approach provides theoretical bounds on information leakage and offers a significant speed-up over the baseline in empirical evaluation.
Online advertising fuels the (seemingly) free internet. However, although users can access most of the web services free of charge, they pay a heavy coston their privacy. They are forced to trust third parties and intermediaries, who not only collect behavioral data but also absorb great amounts of ad revenues. Consequently, more and more users opt out from advertising by resorting to ad blockers, thus costing publishers millions of dollars in lost ad revenues. Albeit there are various privacy-preserving advertising proposals (e.g.,Adnostic, Privad, Brave Ads) from both academia and industry, they all rely on centralized management that users have to blindly trust without being able to audit, while they also fail to guarantee the integrity of the per-formance analytics they provide to advertisers. In this paper, we design and deploy THEMIS, a novel, decentralized and privacy-by-design ad platform that requires zero trust by users. THEMIS (i) provides auditability to its participants, (ii) rewards users for viewing ads, and (iii) allows advertisers to verify the performance and billing reports of their ad campaigns. By leveraging smart contracts and zero-knowledge schemes, we implement a prototype of THEMIS and early performance evaluation results show that it can scale linearly on a multi sidechain setup while it supports more than 51M users on a single-sidechain.
Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a DNN, cloud environments with dedicated hardware support have emerged as critical infrastructure. However, there are many integrity challenges associated with outsourcing computation. Various approaches have been developed to address these challenges, building on trusted execution environments (TEE). Yet, no existing approach scales up to support realistic integrity-preserving DNN model training for heavy workloads (deep architectures and millions of training examples) without sustaining a significant performance hit. To mitigate the time gap between pure TEE (full integrity) and pure GPU (no integrity), we combine random verification of selected computation steps with systematic adjustments of DNN hyper-parameters (e.g., a narrow gradient clipping range), hence limiting the attackers ability to shift the model parameters significantly provided that the step is not selected for verification during its training phase. Experimental results show the new approach achieves 2X to 20X performance improvement over pure TEE based solution while guaranteeing a very high probability of integrity (e.g., 0.999) with respect to state-of-the-art DNN backdoor attacks.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا