Efficient Control Flow Attestation by Speculating on Control Flow Path Representations

2025-07-16

AI Summary

Control-flow authentication (CFA) in embedded systems suffers from high storage and transmission overheads of control-flow logs (CFlogs). Existing speculative compression approaches overlook the impact of address representation on path prediction, limiting achievable compression ratios. This paper proposes RESPEC-CFA, the first CFA architecture to jointly exploit the locality of control-flow addresses and Huffman coding within CFlog speculation. It introduces path-level address prediction, locality-aware symbol substitution, and co-designed encoding to achieve efficient CFlog compression. Experimental results show that RESPEC-CFA achieves a 90.1% CFlog compression ratio when deployed standalone, and up to 99.7% when integrated with existing methods—significantly enhancing CFA’s practicality in resource-constrained environments. The core contribution lies in the unified modeling of address representation locality and compression coding characteristics, thereby overcoming the fundamental compression bottleneck inherent in conventional speculative CFA schemes.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression

Application Category

• Responsible Web: Measurement, analysis, and circumvention of Web censorship
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Control Flow Attestation (CFA) allows remote verification of run-time software integrity in embedded systems. However, CFA is limited by the storage/transmission costs of generated control flow logs (CFlog). Recent work has proposed application-specific optimizations by speculating on likely sub-paths in CFlog and replacing them with reserved symbols at runtime. Albeit effective, prior approaches do not consider the representation of addresses in a control flow path for speculation. This work proposes RESPEC-CFA, an architectural extension for CFA allowing for speculation on (1) the locality of control flows and (2) their Huffman encoding. Alone, RESPEC-CFA reduces CFlog sizes by up to 90.1%. Combined with prior methods, RESPEC-CFA yields reductions of up to 99.7%, representing a significant step toward practical CFA.

Problem

• Reducing storage costs of control flow logs
• Improving efficiency of control flow attestation
• Enhancing speculation on control flow paths

Innovation

• Speculates on control flow locality
• Uses Huffman encoding for paths
• Reduces log sizes by 90.1%