Processor Speculative Execution Security via Selective Cache Flush
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Speculative execution of branching instructions in processors creates vulnerabilities for malicious actors to extract sensitive information, leading to performance losses when remediation methods are implemented to prevent such attacks.
Innovation Solution
Classifying application code as trusted or untrusted based on security classification, and inserting cache flush instructions only before executing untrusted code to mitigate speculative execution threats, thereby reducing performance losses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If speculative execution is enabled to increase program execution efficiency, then processing speed is improved, but system security deteriorates due to vulnerabilities for information extraction attacks
Solution Approach 1:
The patent applies local quality by differentiating between trusted and untrusted code regions, applying cache flush instructions only before untrusted code execution. This localized approach maintains speculative execution performance for trusted code while providing security protection only where needed, resolving the contradiction between speed and security.
2Reliability
If cache flush instructions are inserted before all code execution to prevent speculative execution attacks, then system security is improved, but processing speed deteriorates due to performance losses
Solution Approach 1:
The system performs local quality assessment by classifying code as trusted or untrusted and applies cache flush instructions only in untrusted code regions. This selective application maintains high execution speed for trusted code while providing security protection where needed, resolving the contradiction between security and speed.
Solution Approach 2:
Instead of applying cache flush instructions to all code (excessive action), the patent applies them only to untrusted code portions (partial action). This reduces the overhead and performance impact while maintaining adequate security protection against speculative execution attacks.
3Reliability
If remediation methods are implemented to mitigate speculative execution threats, then system security is improved, but productivity deteriorates due to performance losses
Solution Approach 1:
The patent implements local quality by identifying and marking untrusted code regions, then applying remediation (cache flush instructions) only to those specific regions. This approach maintains high productivity for trusted code paths while providing security protection where needed, resolving the contradiction between security and productivity.
Data Source
AI summary
Improving execution of application program instructions by receiving code having a security classification, determining that the code is untrusted according to the security classification and inserting instructions for a cache flush associated with executing the code.