TEE Core Control for Side-Channel-Resistant Cryptography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing side-channel attack mitigation strategies for cryptographic operations in Trusted Execution Environments (TEEs) incur significant computational overhead, necessitating a more efficient and secure approach.
Innovation Solution
A method that divides cryptographic operations into chunks, issues commands to control processor core characteristics, and verifies that these characteristics are maintained before performing the operations, using techniques like scheduling on high-performance cores or varying core selection to complicate side-channel analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If mitigation strategies such as applying shifting or masking to cryptographic operations are used, then side-channel attack resistance is improved, but computational overhead increases significantly
Solution Approach 1:
The patent introduces an intermediary verification mechanism where the TEE issues commands to control processor core characteristics and verifies compliance before performing cryptographic operations. This intermediary verification layer provides side-channel protection without requiring direct modification of the cryptographic algorithms themselves, thus avoiding their computational overhead.
Solution Approach 2:
The patent changes the operational parameters of the processor core (such as frequency, voltage, or core selection) as a security measure. By dynamically controlling and verifying these physical parameters before cryptographic operations, the system achieves side-channel attack resistance through environmental control rather than algorithmic modification, preserving computational efficiency.
2Reliability
If cryptographic operations are performed inside TEE with logical security isolation, then security of sensitive information is improved, but vulnerability to side-channel attacks increases
Solution Approach 1:
The patent segments the security model into two layers: logical security isolation (TEE vs. REE) and physical environment control (processor core characteristics). By dividing the security approach into these separate segments, the system maintains logical isolation while adding a second layer of physical parameter verification that specifically addresses side-channel vulnerabilities.
Solution Approach 2:
The patent performs preliminary verification of processor core characteristics before allowing cryptographic operations to execute. By checking that the physical environment meets security requirements in advance, the system prevents side-channel attacks without compromising the logical security model, effectively preparing the execution environment beforehand.
Data Source
AI summary
A method for protecting a cryptographic operation on a device from a side-channel attack, the device comprising a processor operable to execute a rich execution environment (REE) and a trusted execution environment (TEE), the method comprising: receiving, at the TEE, a request to perform a cryptographic operation, wherein the cryptographic operation is divisible into a plurality of chunks; issuing, by the TEE, a command to control a characteristic of a core of the processor on which the TEE is to be executed on upon subsequent invocation of the TEE; verifying, by the TEE upon subsequent invocation of the TEE, that the characteristic of the core on which the TEE is executing on corresponds to the command; and responsive to a positive verification, performing, by the TEE, the cryptographic operation on one or more chunks of the plurality of chunks.