AEX-NStep: Probabilistic Interrupt Counting Attacks on Intel SGX

2025-10-16

AI Summary

This paper demonstrates that Intel SGX’s AEX-Notify ISA extension fails to mitigate interrupt-counting side-channel attacks, as its foundational security assumption—“obfuscated forward progress”—does not hold. Method: The authors introduce two novel *probabilistic* interrupt-counting attacks (AEX-NStep), which bypass AEX-Notify’s path-obfuscation guarantee without requiring deterministic single-stepping. By modeling timing variations in AEX-Notify trigger events and combining side-channel analysis with statistical inference, they exploit interrupt counts to recover secrets. Contribution/Results: They successfully extract ECDSA private keys from enclaves protected by AEX-Notify. Experiments confirm the attack’s practicality and robustness—even under non-deterministic execution—thereby establishing, for the first time, that interrupt counting remains a potent threat despite AEX-Notify deployment. This fundamentally undermines the security model of AEX-Notify and exposes a critical flaw in its design assumptions.

Technology Category

• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Distributed Search

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

To mitigate interrupt-based stepping attacks (notably using SGX-Step), Intel introduced AEX-Notify, an ISA extension to Intel SGX that aims to prevent deterministic single-stepping. In this work, we introduce AEX-NStep, the first interrupt counting attack on AEX-Notify-enabled Enclaves. We show that deterministic single-stepping is not required for interrupt counting attacks to be practical and that, therefore, AEX-Notify does not entirely prevent such attacks. We specifically show that one of AEX-Notify's security guarantees, obfuscated forward progress, does not hold, and we introduce two new probabilistic interrupt counting attacks. We use these attacks to construct a practical ECDSA key leakage attack on an AEX-Notify-enabled SGX enclave. Our results extend the original security analysis of AEX-Notify and inform the design of future mitigations.

Problem

• AEX-NStep demonstrates probabilistic interrupt counting attacks on Intel SGX
• It bypasses AEX-Notify's security by exploiting obfuscated forward progress vulnerabilities
• The attack enables practical ECDSA key leakage from protected SGX enclaves

Innovation

• Probabilistic interrupt counting attacks on Intel SGX
• Demonstrating AEX-Notify security guarantees do not hold
• Constructing practical ECDSA key leakage attack