HeatSense: Intelligent Thermal Anomaly Detection for Securing NoC-Enabled MPSoCs

2025-04-15

AI Summary

To address the vulnerability of Network-on-Chip (NoC)-based multiprocessor system-on-chips (MPSoCs) to thermal attacks, this paper proposes a lightweight, router-embedded real-time thermal anomaly detection mechanism. The method introduces a hardware-efficient thermal anomaly spectrum model based on weighted sliding averaging and bit-shift operations—eliminating floating-point arithmetic and dedicated hardware resources. Evaluated on FPGA-accelerated NoC platforms, the approach reduces logic resource utilization by 75% with zero dedicated resource overhead, while incurring only a 10–15% accuracy degradation relative to baseline methods. It achieves an 82% detection accuracy and effectively mitigates severe temperature rises from 3.00°C to 1.90°C. Compared to machine learning–based thermal monitoring schemes, the proposed solution exhibits significantly lower hardware footprint, making it particularly suitable for resource-constrained embedded MPSoC applications.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Multi-Processor System-on-Chips (MPSoCs) are highly vulnerable to thermal attacks that manipulate dynamic thermal management systems. To counter this, we propose an adaptive real-time monitoring mechanism that detects abnormal thermal patterns in chip tiles. Our design space exploration helped identify key thermal features for an efficient anomaly detection module to be implemented at routers of network-enabled MPSoCs. To minimize hardware overhead, we employ weighted moving average (WMA) calculations and bit-shift operations, ensuring a lightweight yet effective implementation. By defining a spectrum of abnormal behaviors, our system successfully detects and mitigates malicious temperature fluctuations, reducing severe cases from 3.00{deg}C to 1.9{deg}C. The anomaly detection module achieves up to 82% of accuracy in detecting thermal attacks, which is only 10-15% less than top-performing machine learning (ML) models like Random Forest. However, our approach reduces hardware usage by up to 75% for logic resources and 100% for specialized resources, making it significantly more efficient than ML-based solutions. This method provides a practical, low-cost solution for resource-constrained environments, ensuring resilience against thermal attacks while maintaining system performance.

Problem

• Detects thermal attacks in NoC-enabled MPSoCs
• Minimizes hardware overhead with lightweight methods
• Improves resilience against malicious temperature fluctuations

Innovation

• Adaptive real-time thermal pattern monitoring
• Lightweight WMA and bit-shift implementation
• Efficient hardware usage with 75% reduction