Sanctum: Minimal Hardware Extensions for Strong Software Isolation

By Victor Costan, Ilia A. Lebedev, Srini Devadas. 2016

656 citations recorded by the source corpus.

How researchers see this paper

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

In Privacy & Security

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, methodology): “TEEs have been instantiated in many forms, including Intel’s SGX-enabled CPUs [208, 116], Arm’s TrustZone [2, 1], and Sanctum on RISC-V [117], each varying in its ability to systematically offer the above facilities.”
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.”
Practical Secure Aggregation for Federated Learning on User-Held Data (2016, background): “Relying only on the non-maliciousness of the bootstrapping round also constitutes minimization of trust: the code implementing this stage is small and could be publicly audited, outsourced to a trusted third party, or implemented via a trusted compute platform offering a remote attestation capabilit”
CacheZoom: How SGX Amplifies The Power of Cache Attacks (2017, neutral): “Symmetric keys can be generated at runtime from a secure random entropy (using RDRAND instruction) and/or transferred through a public secure channel without the attacker knowledge.”
T-SGX: Eradicating Controlled-Channel Attacks Against Enclave Programs (2017, methodology): “Numerous researchers have proposed hardware-based TEE designs, such as TrInc [35], SICE [3], SecureSwitch [58], OASIS [47], TrustLite [32], and Sanctum [11].”
HardFails: Insights into Software-Exploitable Hardware Bugs (2019, background): “A formal veriﬁcation methodology for SGX and Sanctum en-claves under a limited adversary was introduced in [67].”
Keystone: an open framework for architecting trusted execution environments (2020, methodology): “A Trade-offs in existing TEEs Haven [22] Graphene-SGX [31] I n t e l Scone [18] TrustZone [1] Komodo [41] OP-TEE [12] A R M Sanctuary [25] SEV [51] A M D SEV-ES [50] Sanctum [36] TIMBER-V [80] MultiZone [10] R I S C -”
Opaque: An Oblivious and Encrypted Distributed Analytics Platform (2017, methodology): “This parameter can range from as small as the registers (plus Opaque’s enclave code size) to as large as the entire EPC [8, 35] or main memory.”
SgxPectre Attacks: Leaking Enclave Secrets via Speculative Execution (2018, background): “ode. Side-channel defenses. Existing countermeasures to side-channel attacks can be categorized into three classes: hardware solutions, system solutions, and application solutions. Hardware solutions [76, 77, 21, 47, 45, 18]requiremodiﬁcationoftheprocessors,whicharetypically effective, but are limit”
Software Grand Exposure: SGX Cache Attacks Are Practical (2017, methodology): “Another approach against information leakage is obviously hardware re-design as taken by Sanctum [15].”
Inferring Fine-grained Control Flow Inside SGX Enclaves with Branch Shadowing (2016, background): “As a result, we could demonstrate our attack by breaking recent security constructs, including ORAM schemes, Sanctum, SGX-Shield, and T-SGX.”
IRON: Functional Encryption using Intel SGX (2017, methodology): “on implementing Iron with Intel SGX, in principle the system could be instantiated using other isolated execution environments that also support remote software attestation, such as XOM [40], AEGIS [55, 56], Bastion [16], Ascend [22] and Sanctum [21].”
Sealed-Glass Proofs: Using Transparent Enclaves to Prove and Sell Knowledge (2017, background): “Such attacks are not unique to SGX, and a number of defenses have been developed over the years [6]–[9], usually to protect highly sensitive cryptographic code.”
Leaky Cauldron on the Dark Land: Understanding Memory Side-Channel Hazards in SGX (2017, background): “Sanctum [15] is a new hardware design that aims to protect against both last-level cache attacks and page-table based attacks.”
This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Ryoan: a Distributed Sandbox for Untrusted Computation on Secret Data Ryoan: a Distributed Sandbox for Untrusted Computation on Secret Data (neutral): “Such channels are themselves technically difﬁcult and often require dedicated systems to address adequately [33, 35, 44, 49, 80].”
Jump over ASLR: Attacking branch predictors to bypass ASLR (2016, background): “Another relevant application of a user-level ASLR attack is to perform layout de-randomization in isolated execution environments, where application secrets are protected inside enclaves or compartments [37], [38], [39], [40].”
Komodo: Using verification to disentangle secure-enclave hardware from software (2017, background): “We note that Sanctum [19] (a modified RISC-V CPU) meets all the above requirements, with the caveat that physical attacks are out of scope.”