Cluster-BPI: Efficient Fine-Grain Blind Power Identification for Defending against Hardware Thermal Trojans in Multicore SoCs

• URL: http://arxiv.org/abs/2409.18921v1
• Date: Fri, 27 Sep 2024 17:11:29 GMT
• Title: Cluster-BPI: Efficient Fine-Grain Blind Power Identification for Defending against Hardware Thermal Trojans in Multicore SoCs
• Abstract summary: Clustering Blind Power Identification (ICBPI) is designed to improve the sensitivity and robustness of the traditional Blind Power Identification (BPI) method. ICBPI significantly enhances accuracy, reducing error rates by 77.56% compared to the original BPI and by 68.44% compared to the state-of-the-art BPISS method.
• Score: 0.562479170374811
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern multicore System-on-Chips (SoCs) feature hardware monitoring mechanisms that measure total power consumption. However, these aggregate measurements are often insufficient for fine-grained thermal and power management. This paper presents an enhanced Clustering Blind Power Identification (ICBPI) approach, designed to improve the sensitivity and robustness of the traditional Blind Power Identification (BPI) method. BPI estimates the power consumption of individual cores and models the thermal behavior of an SoC using only thermal sensor data and total power measurements. The proposed ICBPI approach refines BPI's initialization process, particularly improving the non-negative matrix factorization (NNMF) step, which is critical to the accuracy of BPI. ICBPI introduces density-based spatial clustering of applications with noise (DBSCAN) to better align temperature and power consumption data, thereby providing more accurate power consumption estimates. We validate the ICBPI method through two key tasks. The first task evaluates power estimation accuracy across four different multicore architectures, including a heterogeneous processor. Results show that ICBPI significantly enhances accuracy, reducing error rates by 77.56% compared to the original BPI and by 68.44% compared to the state-of-the-art BPISS method. The second task focuses on improving the detection and localization of malicious thermal sensor attacks in heterogeneous processors. The results demonstrate that ICBPI enhances the security and robustness of multicore SoCs against such attacks.

Related papers

• Joint Sensor Deployment and Physics-Informed Graph Transformer for Smart Grid Attack Detection [7.8160642765456165]
  A novel physics-informed graph transformer network (PIGTN)-based detection model is proposed.<n>By incorporating AC power flow constraints, the proposed PIGTN-based detection model generalizes well to unseen attacks.
  arXiv  Detail & Related papers  (2026-02-16T06:37:19Z)
• Information-Bottleneck Driven Binary Neural Network for Change Detection [53.866667209237434]
  Binarized Change Detection (BiCD) is the first binary neural network (BNN) designed specifically for change detection.<n>We introduce an auxiliary objective based on the Information Bottleneck (IB) principle, guiding the encoder to retain essential input information.<n>BiCD establishes a new benchmark for BNN-based change detection, achieving state-of-the-art performance in this domain.
  arXiv  Detail & Related papers  (2025-07-04T11:56:16Z)
• CPINN-ABPI: Physics-Informed Neural Networks for Accurate Power Estimation in MPSoCs [0.562479170374811]
  Alternative Blind Power Identification (ABPI) theoretically eliminates the dependence on steady-state temperatures.<n>ABPI performance has remained unverified in actual hardware implementations.<n>We introduce a novel approach that integrates Custom Physics-Informed Neural Networks (CPINNs) with the underlying thermal model of ABPI.
  arXiv  Detail & Related papers  (2025-05-28T15:22:15Z)
• Optimizing Carbon Footprint in ICT through Swarm Intelligence with Algorithmic Complexity [0.0]
  Global emissions from fossil fuel combustion and cement production were recorded in 2022, signaling a resurgence to pre-pandemic levels. This shows the need for further exploration of swarm intelligence applications to measure and optimize the carbon footprint within ICT.
  arXiv  Detail & Related papers  (2025-01-20T02:34:55Z)
• A High-accuracy Calibration Method of Transient TSEPs for Power Semiconductor Devices [2.7446241148152257]
  The thermal sensitive electrical parameter (TSEP) method is crucial for enhancing the reliability of power devices. We propose a high-accuracy calibration method for transient TSEPs. Compared with conventional calibration methods, the mean absolute error is reduced by over 30%.
  arXiv  Detail & Related papers  (2025-01-09T06:56:47Z)
• A Reinforcement Learning-Based Task Mapping Method to Improve the Reliability of Clustered Manycores [0.0]
  We propose a reinforcement learning (RL)-based task mapping method to improve reliability of manycore systems. The method consists of three steps including bin packing, task-to-bin mapping, and task-to-core mapping. The effectiveness of the proposed technique is evaluated on 16, 32, and 64 cores systems using SPLASH2 and PARSEC benchmark suite applications.
  arXiv  Detail & Related papers  (2024-12-26T20:08:10Z)
• Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression [63.23578860867408]
  We investigate how to integrate the evaluations of importance and sparsity scores into a single stage. We present OFB, a cost-efficient approach that simultaneously evaluates both importance and sparsity scores. Experiments demonstrate that OFB can achieve superior compression performance over state-of-the-art searching-based and pruning-based methods.
  arXiv  Detail & Related papers  (2024-03-23T13:22:36Z)
• Blue and Green-Mode Energy-Efficient Nanoparticle-Based Chemiresistive Sensor Array Realized by Rapid Ensemble Learning [0.5890690947925292]
  This study introduces an optimization strategy that employs a rapid ensemble learning-based model committee approach. A weighted voting mechanism is introduced to aggregate the models' opinions in sensor selection. The strategy is validated through theoretical calculations and Monte Carlo simulations, demonstrating its effectiveness and accuracy.
  arXiv  Detail & Related papers  (2024-03-03T23:38:37Z)
• Fault Detection for Non-Condensing Boilers using Simulated Building Automation System Sensor Data [0.0]
  Building performance degrades significantly after commissioning, resulting in increased energy consumption and associated greenhouse gas emissions. Continuous Commissioning using existing sensor networks and IoT devices has the potential to minimize this waste. A review of boiler performance studies has been used to develop a set of common faults and degraded performance conditions. The data is used for training and testing fault classification using K-nearest neighbour, Decision tree, Random Forest, and Support Vector Machines.
  arXiv  Detail & Related papers  (2022-05-13T18:47:16Z)
• Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring [17.155316991045765]
  Photoplethysmography (volution) sensors allow for non-invasive and comfortable heart-rate (HR) monitoring. Motion Artifacts (MAs) severely impact the monitoring accuracy, causing high variability in the skin-to-sensor interface. We propose a computationally lightweight yet robust deep learning-based approach for PPG-based HR estimation. We validate our approaches on two benchmark datasets, achieving as low as 3.84 Beats per Minute (BPM) of Mean Absolute Error (MAE) on PPGDalia.
  arXiv  Detail & Related papers  (2022-03-01T17:04:28Z)
• Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise [6.857190736208506]
  In this work, we focus on estimating the power output of a Combined Heat and Power machine of a medium-sized company facility. As the facility is fully instrumented and sensor measurements from the CHP are available, we generate the training labels in an automated fashion. We propose a novel multi-task deep learning approach that jointly trains a classifier and an autoencoder with a shared embedding representation.
  arXiv  Detail & Related papers  (2021-05-01T21:45:42Z)
• Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration [57.568461777747515]
  We introduce a novel calibration method, Parametrized Temperature Scaling (PTS) We demonstrate that the performance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by their intrinsic expressive power. We show with extensive experiments that our novel accuracy-preserving approach consistently outperforms existing algorithms across a large number of model architectures, datasets and metrics.
  arXiv  Detail & Related papers  (2021-02-24T10:18:30Z)
• Smart non-intrusive appliance identification using a novel local power histogramming descriptor with an improved k-nearest neighbors classifier [2.389598109913753]
  This paper proposes a smart NILM system based on a novel local power histogramming (LPH) descriptor. Specifically, short local histograms are drawn to represent individual appliance consumption signatures. An improved k-nearest neighbors (IKNN) algorithm is presented to reduce the learning time and improve the classification performance.
  arXiv  Detail & Related papers  (2021-02-09T13:12:20Z)
• EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification [123.93460670568554]
  This paper proposes a novel convolutional neural network (CNN) architecture for accurate and robust EEG-based motor imagery (MI) classification. The proposed CNN model, namely EEG-Inception, is built on the backbone of the Inception-Time network. The proposed network is an end-to-end classification, as it takes the raw EEG signals as the input and does not require complex EEG signal-preprocessing.
  arXiv  Detail & Related papers  (2021-01-24T19:03:10Z)
• Uncertainty-Aware Deep Calibrated Salient Object Detection [74.58153220370527]
  Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. These methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. We introduce an uncertaintyaware deep SOD network, and propose two strategies to prevent deep SOD networks from being overconfident.
  arXiv  Detail & Related papers  (2020-12-10T23:28:36Z)
• Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection [66.05992706105224]
  In this paper, an effective anomaly detection framework is proposed utilizing Bayesian Optimization technique. The performance of the considered algorithms is evaluated using the ISCX 2012 dataset. Experimental results show the effectiveness of the proposed framework in term of accuracy rate, precision, low-false alarm rate, and recall.
  arXiv  Detail & Related papers  (2020-08-05T19:29:35Z)
• Towards High Performance Human Keypoint Detection [87.1034745775229]
  We find that context information plays an important role in reasoning human body configuration and invisible keypoints. Inspired by this, we propose a cascaded context mixer ( CCM) which efficiently integrates spatial and channel context information. To maximize CCM's representation capability, we develop a hard-negative person detection mining strategy and a joint-training strategy. We present several sub-pixel refinement techniques for postprocessing keypoint predictions to improve detection accuracy.
  arXiv  Detail & Related papers  (2020-02-03T02:24:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.