Innovative instructions and software model for isolated execution

By Francis X. McKeen, Ilya Alexandrovich, Alex Berenzon, Carlos V. Rozas, Hisham Shafi, Vedvyas Shanbhogue, Uday R. Savagaonkar. 2013

1,296 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Signal Processing

Citations in the corpus

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (2018, background): “g, Intel SGX [34], ARM TrustZone [1] or Sanctum [11] offer a more pragmatic solution to this dearth of trust.”
Ekiden: A Platform for Confidentiality-Preserving, Trustworthy, and Performant Smart Contracts (2018, positive): “Ekiden is implemented with Intel SGX [8, 40, 61], a specific provider of TEEs, but we emphasize that it may use any comparable TEE with attestation capabilities.”
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, background): “A secure enclave is a set of software and hardware features that together provide an isolated execution environment that enables a set of strong guarantees regarding security for applications running inside the enclave [109].”
VC3: Trustworthy Data Analytics in the Cloud Using SGX (2015, methodology): “B. Intel SGX SGX [3], [32], [41] is a set of x86-64 ISA extensions that makes it possible to set up protected execution environments (called enclaves) without requiring trust in anything but the processor and the code users place inside their enclaves.”
Shredder: Learning Noise Distributions to Protect Inference Privacy (2019, methodology): “s function of the optimization that ﬁnds the noise. Trusted execution environments. Several research propose running machine learning algorithms in in trusted execution environments such as Intel SGX [55] and ARM TrustZone [56] to address the same remote inference privacy [57, 58, 59, 60] as well as”
A Memory Encryption Engine Suitable for General Purpose Processors (2016, background): “To illustrate why SGX needs full protection for (part of) the DRAM, we provide a brief outline of this technology (see [3], [4], [16], [12] for details).”
Graviton: Trusted Execution Environments on GPUs (2018, background): “Intel SGX [28] is the latest in this line of work, but stands out because it provides comprehensive protection and is already available in client CPUs and public cloud platforms.”
Innovative Technology for CPU Based Attestation and Sealing (2013, background): “Secret owners that accept SGX ’s security mode l can rely on these instructions to report back the TCB in charge of the secrets.”
Tesseract: Real-Time Cryptocurrency Exchange using Trusted Hardware (2017, background): “For more information on the SGX architecture, see [1, 44, 43, 61].”
Shielding Applications from an Untrusted Cloud with Haven (2014, methodology): “It leverages Intel software guard extensions (SGX) [Intel Corp. 2013, 2014b; McKeen et al. 2013], a set of new instructions and memory access changes summarized in Section 3.1.”
SgxPectre Attacks: Leaking Enclave Secrets via Speculative Execution (2018, background): “y guarantees. Although SGX is still in its infancy, the promise of shielded execution has encouraged researchers and practitioners to develop various new applications to utilize these features (e.g., [2, 22, 51, 54, 59, 68, 69, 85, 88]), and new software tools or frameworks (e.g., [4, 5, 9, 24, 43, ”
M2R: Enabling Stronger Privacy in MapReduce Computation (2015, methodology): “Advanced hardware-based techniques include Intel SGX [40] and Bastion [12] provide a hardware protected secure mode in which applications can be executed at hardware speed.”
Opaque: An Oblivious and Encrypted Distributed Analytics Platform (2017, background): “Much of the oblivious costs are due to the fact that Intel SGX is not set up for big data analytics processing; future architectures [8, 21, 35] providing larger and oblivious enclave memory will reduce this cost significantly.”
SgxPectre: Stealing Intel Secrets from SGX Enclaves Via Speculative Execution (2018, background): “…of shielded execution has encouraged researchers and practitioners to develop various new applications to utilize these features ( e.g. , [2, 22, 51, 54, 59, 68, 69, 85, 88]), and new software tools or frameworks ( e.g. , [4, 5, 9, 24, 43, 50, 61, 65, 67, 72, 80]) to help developers adopt this…”
IRON: Functional Encryption using Intel SGX (2017, methodology): “specifications are detailed and complex [32, 43].”
Preventing Page Faults from Telling Your Secrets (2016, background): “As a recourse, we conduct all our experiments on P OD A RCH [44]; a system similar to previous hypervisor solutions [18] and conceptually similar to SGX.”
BranchScope: A New Side-Channel Attack on Directional Branch Predictor (2018, background): “BranchScope can be directly leveraged to target a system that supports isolated execution, such as Intel’s SGX [42], or be used as a general side channel attack in conventional environments.”