iThermTroj: Exploiting Intermittent Thermal Trojans in Multi-Processor System-on-Chips

2025-07-07

AI Summary

Intermittent thermal Trojan attacks on multi-processor SoCs—particularly challenging to detect in mobile scenarios—are shown to evade conventional threshold-based thermal monitoring by stochastically triggering temperature sensor data corruption. This work exposes a critical vulnerability in existing defenses against stealthy thermal manipulation. To address this, we propose the first formal model of intermittent thermal Trojans and design a lightweight, runtime anomaly detection framework leveraging micro-machine learning to monitor temperature-sensor tampering with high sensitivity. Experimental evaluation demonstrates detection rate improvements of 29.4%, 17.2%, and 14.3% across varying corruption ratios, achieves ±0.8°C full-range protection resolution, and guarantees 100% detection of out-of-spec temperature deviations.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Hardware-aware ML
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Thermal Trojan attacks present a pressing concern for the security and reliability of System-on-Chips (SoCs), especially in mobile applications. The situation becomes more complicated when such attacks are more evasive and operate sporadically to stay hidden from detection mechanisms. In this paper, we introduce Intermittent Thermal Trojans (iThermTroj) that exploit the chips' thermal information in a random time-triggered manner. According to our experiments, iThermTroj attack can easily bypass available threshold-based thermal Trojan detection solutions. We investigate SoC vulnerabilities to variations of iThermTroj through an in-depth analysis of Trojan activation and duration scenarios. We also propose a set of tiny Machine Learning classifiers for run-time anomaly detection to protect SoCs against such intermittent thermal Trojan attacks. Compared to existing methods, our approach improves the attack detection rate by 29.4%, 17.2%, and 14.3% in scenarios where iThermTroj manipulates up to 80%, 60%, and 40% of SoC's thermal data, respectively. Additionally, our method increases the full protection resolution to 0.8 degrees Celsius, meaning that any temperature manipulations exceeding $pm 0.8$ degrees will be detected with 100% accuracy.

Problem

• Detecting evasive intermittent thermal Trojan attacks in SoCs
• Bypassing threshold-based thermal Trojan detection mechanisms
• Protecting SoCs with machine learning for runtime anomaly detection

Innovation

• Random time-triggered thermal Trojan exploitation
• Tiny Machine Learning for anomaly detection
• Improved detection rate and resolution accuracy