Data Marking for Speculative Execution Side-Channel Resistance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing software-based and hardware-based mitigation strategies for side-channel attacks (SCAs) face challenges in effectively preventing data leakage due to speculative execution and microarchitectural vulnerabilities, with high performance overhead or intrusive modifications.

Innovation Solution

A data-centric security calculation method and system that marks sensitive memory blocks using a flag in the page table entry (PTE) and employs a delayed update mechanism in the reorder buffer (ROB) to prevent speculative execution of dependent instructions, minimizing performance impact.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual serializing instructions are inserted to prevent speculative execution, then security against transient-execution attacks is improved, but performance overhead increases and manual identification of vulnerable branches is difficult

Engineering Contradiction:
ImprovesecurityVSAvoidperformance
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system automatically identifies sensitive memory blocks and inserts serializing instructions without manual intervention. The OS detects confidential data in memory and autonomously generates the necessary security instructions, eliminating the need for developers to manually identify vulnerable branches while maintaining security protection.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent introduces an intermediary mechanism between the application and hardware - the OS-level memory-safe function that acts as a mediator. This intermediary automatically manages the marking of sensitive memory blocks and coordination with hardware ROB, preventing transient-execution attacks without requiring manual code modification or direct hardware intervention.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If compiler-automated protection for all branches is implemented, then security coverage is improved, but performance overhead becomes excessive

Engineering Contradiction:
Improvesecurity coverageVSAvoidperformance overhead
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

Instead of applying uniform protection to all branches, the system applies protection locally and selectively only to memory operations involving confidential data. The OS identifies specific sensitive memory blocks and marks them individually, ensuring that only necessary instructions are serialized, thereby minimizing performance overhead while maintaining comprehensive security coverage.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements partial protection by focusing only on memory operations that access confidential data rather than protecting all branches excessively. The OS detects and marks only the necessary sensitive memory blocks, applying security measures precisely where needed without over-protection of non-sensitive operations.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If hardware structures are added to obscure microarchitectural status changes, then security against SCAs is improved, but hardware modification becomes intrusive with huge performance overhead

Engineering Contradiction:
ImprovesecurityVSAvoidhardware modification
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses the OS as an intermediary layer between software and hardware, avoiding direct hardware modification. The OS marks sensitive memory blocks and communicates with the hardware ROB through standard interfaces, enabling security protection without intrusive hardware changes or complex microarchitectural modifications.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system leverages existing hardware structures (ROB, scoreboard) for multiple purposes - both their original function of enabling out-of-order execution and the new security function of preventing transient-execution attacks. By utilizing existing hardware capabilities rather than adding new structures, the patent avoids increasing device complexity while maintaining security.

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Productivity

If out-of-order execution is enabled to improve performance, then processing speed is improved, but vulnerability to speculative execution attacks increases

Engineering Contradiction:
Improveprocessing speedVSAvoidvulnerability to attacks
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system takes preliminary anti-action by marking sensitive memory blocks before speculative execution can occur. The OS identifies and marks confidential data in memory ahead of time, and the hardware ROB detects these marked blocks to prevent speculative execution of dependent instructions, thereby neutralizing the vulnerability before it can be exploited while maintaining out-of-order execution benefits.

Inventive Principle:
Principle #9Preliminary anti-action

Solution Approach 2:

The patent implements a feedback mechanism where the ROB monitors instruction execution and detects accesses to marked sensitive memory blocks. When such accesses are detected during speculative execution, the system provides feedback to stall or abort the speculative instructions, dynamically adjusting execution based on security requirements while preserving performance for non-sensitive operations.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS12530451B2Security calculation method and system for side channel resistance based on data marking
Publication Date: 2026.01.20 NANHU LAB
  • US12530451B2 patent drawing
  • US12530451B2 patent drawing

AI summary

A security calculation method and system for side channel resistance based on data marking is used to defend against a microarchitectural side-channel attack (SCA), particularly a transient-execution attack. The method is data-centric, and based on data marking. Through the data marking (page table entry (PTE) marking and instruction marking), and a delayed update mechanism dependent on the data marking, the method ensures that any subsequent instructions dependent on a memory-sensitive instruction are not executed in speculative execution, thereby preventing confidential data from being leaked when a conditional branch outcome is unknown, effectively resisting the SCA, improving the security, and minimizing the impact on central processing unit (CPU) performance.