CacheZoom: How SGX Amplifies the Power of Cache Attacks
In modern computing environments, hardware resources are commonly shared, and parallel computation is widely used. Parallel tasks can cause privacy and security problems if proper isolation is not enforced. Intel proposed SGX to create a trusted execution
- PDF / 1,020,689 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 76 Downloads / 188 Views
Abstract. In modern computing environments, hardware resources are commonly shared, and parallel computation is widely used. Parallel tasks can cause privacy and security problems if proper isolation is not enforced. Intel proposed SGX to create a trusted execution environment within the processor. SGX relies on the hardware, and claims runtime protection even if the OS and other software components are malicious. However, SGX disregards side-channel attacks. We introduce a powerful cache side-channel attack that provides system adversaries a high resolution channel. Our attack tool named CacheZoom is able to virtually track all memory accesses of SGX enclaves with high spatial and temporal precision. As proof of concept, we demonstrate AES key recovery attacks on commonly used implementations including those that were believed to be resistant in previous scenarios. Our results show that SGX cannot protect critical data sensitive computations, and efficient AES key recovery is possible in a practical environment. In contrast to previous works which require hundreds of measurements, this is the first cache side-channel attack on a real system that can recover AES keys with a minimal number of measurements. We can successfully recover AES keys from T-Table based implementations with as few as ten measurements.
1
Motivation
In the parallel computing environment, processes with various trust and criticality levels are allowed to run concurrently and share system resources. Proliferation of cloud computing technology elevated these phenomena to the next level. Cloud computers running many different services authored by various providers process user information on the same hardware. Traditionally, the operating system (OS) provides security and privacy services. In cloud computing, cloud providers and the hypervisor also become part of the Trusted Computing Base (TCB). Due to the high complexity and various attack surfaces in modern computing systems, keeping an entire system secure is usually unrealistic [19,33]. One way to reduce the TCB is to outsource security-critical services to Secure Elements (SE), a separate trusted hardware which usually undergoes rigorous auditing. Trusted Platform Modules (TPM), for example, provide services such as cryptography, secure boot, sealing data and attestation beyond the authority of the OS [39]. However, SEs come with their own drawbacks: they are static c International Association for Cryptologic Research 2017 W. Fischer and N. Homma (Eds.): CHES 2017, LNCS 10529, pp. 69–90, 2017. DOI: 10.1007/978-3-319-66787-4 4
70
A. Moghimi et al.
components and connected to the CPU over an untrusted bus. Trusted Execution Environments (TEE) are an alternative, which provide similar services within the CPU. A TEE is an isolated environment to run software with a higher trust level than the OS. The software running inside a TEE has full access to the system resources while it is protected from other applications and the OS. Examples include ARM TrustZone [4] and Intel Software Guard eXten
Data Loading...
