Efficient machine learning methods for hardware Trojan detection using instruction-level power character

Hardware Trojans (HTs) pose a serious threat to integrated circuit (IC) security. Detection of HTs is extremely challenging due to their stealthy nature. Side-channel analysis techniques have emerged as promising approaches for HT detection by observing anomalies in physical parameters like power or delay. More recently, machine learning (ML) methods have been explored to enhance the accuracy and efficiency of side-channel based HT detection. Background: This paper presents a novel approach using machine learning techniques to detect stealthy hardware Trojans through side-channel analysis. Hardware Trojans, malicious modifications inserted into integrated circuits during manufacturing, pose significant threats to the integrity and security of electronic systems. Traditional methods of detecting these Trojans often rely on known signatures or specific patterns, making them ineffective against subtle and sophisticated attacks. Method: This paper provides a comprehensive review of research advancements in applying ML for side-channel based HT detection. First, an overview of HT attacks, their classification, threat models and detection challenges is presented. Next, various side-channel parameters like power, temperature, delay and electromagnetic emanations used for HT detection are discussed along with their merits and demerits. Furthermore, the application of supervised, unsupervised and semi-supervised ML algorithms for automated feature extraction and intelligent decision making is elucidated in detail. Result: Specifically, the data collection strategies, feature extraction techniques, ML models and performance evaluation metrics adopted in existing literature are critically reviewed. In addition, the limitations of current approaches and promising future research directions like on-chip ML implementation, hierarchical ML and explainable ML models tailored for HT detection are highlighted. Conclusion: Case studies on benchmark circuits are also presented to demonstrate the efficacy of ML-based side-channel HT detection methods. Through an extensive literature review and incisive analysis, this paper provides contemporary insights on the advancement of ML techniques to enable robust side-channel based HT detection for securing next-generation ICs.

Recently, there are various methods for detecting the hardware trojans (HTs) in the integrated circuits (ICs). The circuit's logic representations of different types, structures, and functional characteristics should be different. Each type of circuit has its' own performance characteristics according to its' purpose. However, the traditional HTs detection methods adopt the same approach to deal with the multi-purpose hardware trojan. At the same time, as the scale of integrated circuits growing, the structures are more complex, and the functions are more refined. The current situation makes the traditional HTs detection methods weaker and even unfeasible. Therefore, we propose an HTs classified locating method based on machine learning, named ML-HTCL, which belongs to the static detection and locating method. In ML-HTCL, different purpose HTs were represented by different features. Due to the different features, the ML-HTCL employs the multi-layer BP neural network for the control signal type HTs and the one-class SVM for the information leakage HTs, respectively. To deal with the HTs completely, the boundary nets are considered for all data set, while those were ignored by the most existing methods due to the high detection error rate. After detection, the HTs' precise locations were achieved. To evaluate the ML-HTCL, 17 gate-level netlist benchmarks are used for training and testing by leave-one-out cross-validation. From the results, the ML-HTCL reaches 85.05% of TPR and 73.91% of TNR for all kinds of HTs, which performs better than the most existing methods.

Data is one of the most important limiting factors of deep machine learning (ML) model in drilling applications. Though a big size of historical data can be available, high-quality cleaned and labeled data is usually limited. In this case study, we show that with limited labeled data, physics-based data augmentation combined with unsupervised learning significantly improves both stability and accuracy in bit wear ML model. It provides a pathway to overcome labeled data shortage and field data quality limitations. Labeled bit wear data is usually limited because only the final bit dull state can be labeled using dull photos for the entire drilling distance. To overcome this difficulty, an encoder-decoder unsupervised ML framework based on Bi-directional LSTM architecture is first applied to the data of entire drilling distance to extract and maximize data learnings. Then, a physics-based wear estimator is implemented in the learned latent space to augment labeled wear dataset, guided by true wear labels and offset-well data. Weighting factor in loss function is applied to optimize augmented and true datasets in final supervised learning step. The proposed real-time bit wear model is built on a combination of physics-based data augmentation and unsupervised data learning method. The model is applied on multiple field bit runs. Results show that by implementing the unsupervised data learnings only, the prediction accuracy is improved by 30% compared to the baseline ML model. By combining physics-based augmentation, the accuracy is further improved by 10%. More importantly, adding physics-based data augmentation significantly reduces prediction variance and unphysical wear outputs, therefore improving prediction stability by more than 30%. It should be noted that the prediction stability of AI/ML model is crucial in real-time application and decision making. The results show physics-based data augmentation not only increases the size of label dataset and prevents model overfitting, but also applies physics-based guidance to the ML model effectively. It is learned weighting factor plays a crucial role in balancing loss contributions from true wear labels and physics-based labels. While low weighting factor of physics-based labels diminishes the augmented data, high weighting factor disrespects the true wear labels leading to a high prediction bias. Overall, the bit wear model study shows physic-based data augmentation combined with unsupervised data learning can effectively improve model accuracy, stability, and overcome labeled data shortage difficulty. The proposed paper shows a case study for the bit wear ML model using a combination of physics-based data augmentation and unsupervised data learning. While labeled data is one of the major challenges of ML models in many drilling applications, this study provides a pathway to improve both accuracy and stability of deep ML models with limited labeled data.

Hardware Trojan (HT) has recently drawn much attention in both industry and academia due to the global outsourcing trend in semiconductor manufacturing, where a malicious logic can be inserted into the security critical ICs at almost any stages. HT severity mainly stems from its low-cost and stealthy nature where the HT only functions at a strict condition to purposely alter the logic or physical behavior for leaking secrets. This fact makes HT detection very challenging in practice. In this paper, we propose a novel HT detection technique based on machine learning approach. The described solution is constructed over one-class SVM and is shown to be more robust compared to the template based detection techniques. An unsupervised approach is also applied in our solution for mitigating the golden model dependencies. To evaluate the solution, a practical HT design was inserted into an AES coprocessor implemented in a Xilinx FPGA. Based on the partial reconfiguration, the HT size can be dynamically changed without altering cipher part, which helps to precisely evaluate the HT influence. The experimental results have shown that our proposed detection technique achieve a high performance accuracy.

Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

PurposeAtherosclerosis plays a significant role in the initiation of coronary artery aneurysms (CAA). Although the treatment options for this kind of vascular disease are developing, there are challenges and limitations in both selecting and applying sufficient medical solutions. For surgical interventions, that are novel therapies, non-invasive specific patient-based studies could lead to obtaining more promising results. Despite medical and pathological tests, these pre-surgical investigations require special biomedical and computer-aided engineering techniques. In this study, a machine learning (ML) model is proposed for the non-invasive detection of atherosclerotic CAA for the first time.MethodsThe database for study was collected from hemodynamic analysis and computed tomography angiography (CTA) of 80 CAAs from 61 patients, approved by the Institutional Review Board (IRB). The proposed ML model is formulated for learning by a one-class support vector machine (1SVM) that is a field of ML to provide techniques for outlier and anomaly detection.ResultsThe applied ML algorithms yield reasonable results with high and significant accuracy in designing a procedure for the non-invasive diagnosis of atherosclerotic aneurysms. This proposed method could be employed as a unique artificial intelligence (AI) tool for assurance in clinical decision-making procedures for surgical intervention treatment methods in the future.ConclusionsThe non-invasive diagnosis of the atherosclerotic CAAs, which is one of the vital factors in the accomplishment of endovascular surgeries, is important due to some clinical decisions. Although there is no accurate tool for managing this kind of diagnosis, an ML model that can decrease the probability of endovascular surgical failures, death risk, and post-operational complications is proposed in this study. The model is able to increase the clinical decision accuracy for low-risk selection of treatment options.

There is limited understanding of the link between exposure to heavy metals and ischemic stroke (IS). This research aimed to develop efficient and interpretable machine learning (ML) models to associate the relationship between exposure to heavy metals and IS. The data of this research were obtained from the National Health and Nutrition Examination Survey (US NHANES, 2003-2018) database. Seven ML models were used to identify IS caused by exposure to heavy metals. To assess the strength of the models, we employed 10-fold cross-validation, the area under the curve (AUC), F1 scores, Brier scores, Matthews correlation coefficient (MCC), precision-recall (PR) curves, and decision curve analysis (DCA) curves. Following these tests, the best-performing model was selected. Finally, the DALEX package was used for feature explanation and decision-making visualization. A total of 15,575 participants were involved in this study. The best-performing ML models, which included logistic regression (LR) (AUC: 0.796) and XGBoost (AUC: 0.789), were selected. The DALEX package revealed that age, total mercury in blood, poverty-to-income ratio (PIR), and cadmium were the most significant contributors to IS in the logistic regression and XGBoost models. The logistic regression and XGBoost models showed high efficiency, accuracy, and robustness in identifying associations between heavy metal exposure and IS in NHANES 2003-2018 participants.

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

Systematic literature review of machine learning based software development effort estimation models

Integrated Circuits (ICs) are suffering severer threats caused by Hardware Trojans (HTs), some of which hide in routine operations by coercing firmware or hardware. Along with conventional side-channel detection not always getting golden-chip, HTs become more difficult to detect. An improved Support Vector Machine (SVM) machine learning frameworks for this is proposed using system-level side-channel analysis. Cross validation experimental results on Field Programmable Gate Array (FPGA) show that in the condition of golden-chip, supervised SVM achieves 85.8% test accuracy in average. After grouping, outlier-removing and normalization, it rises by 4%. Even if golden-chip is out of hand, semi-supervised SVM has accuracy to judge HTs existence, averaging in 52.9%-79.5% under different test modes. Comparing with existing researches, this work verifies the efficiency of SVM for HT detection in instruction level, and points out the relationship between diversified learning conditions with detection performance.

The globalization of the integrated circuit (IC) supply chain has moved most of the design, fabrication, and testing process from a single trusted entity to various untrusted third-party entities worldwide. The risk of using untrusted third-Party Intellectual Property (3PIP) is the possibility for adversaries to insert malicious modifications known as Hardware Trojans (HTs). These HTs can compromise the integrity, deteriorate the performance, deny the service, and alter the functionality of the design. While numerous HT detection methods have been proposed in the literature, the crucial task of HT localization is overlooked. Moreover, a few existing HT localization methods have several weaknesses: reliance on a golden reference, inability to generalize for all types of HT, lack of scalability, low localization resolution, and manual feature engineering/property definition. To overcome their shortcomings, we propose a novel, golden reference-free HT localization method at the pre-silicon stage by leveraging graph convolutional network (GCN). In this work, we convert the circuit design into its intrinsic data structure, graph, and extract the node attributes. Afterward, the graph convolution performs automatic feature extraction for nodes to classify the nodes as Trojan or benign. Our approach is automated and does not burden the designer with manual code review. It locates the Trojan signals with 99.6% accuracy, 93.1% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> -score, and a false-positive rate below 0.009%.

Accurate estimation of reference evapotranspiration (ETo) plays a vital role in irrigation and water resource planning. The Penman–Monteith method recommended by the Food and Agriculture Organization (FAO PM56) is widely used and considered a standard to calculate ETo. However, FAO PM56 cannot be used with limited meteorological variables, so it is compulsory to choose an alternative model for ETo estimation, which requires fewer variables. This study built ten machine learning (ML) models based on multi-function, neural network, and tree-based structure against the FAO PM56 method. For this purpose, time series temperature data on a monthly scale are only used to train ML models. The developed ML models were applied to estimate ETo at different test stations and the obtained results were compared with the FAO PM56 method to verify and validate their performance in ETo estimation for the selected stations. In addition, multiple statistical indicators, including root-mean-square error (RMSE), coefficient of determination (R2), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and correlation coefficient (r) were calculated to compare the performance of each ML model on ETo estimation. Among the applied ML models, the ETo tree boost (TB) ML model outperformed the other ML models in estimating ETo in diverse climatic conditions based on statistical indicators (R2, NSE, r, RMSE, and MAE). Moreover, the observed R2, NSE, and r were the highest for the TB ML model, while RMSE and MAE were found to be the lowest at the study sites compared to other applied ML models. Lastly, ETo point data yielded from the TB ML model was used in an interpolation process to create monthly and annual ETo maps. Based on the ETo maps, this study suggests mainly a focus on areas with high ETo values and proper irrigation scheduling of crops to ensure water sustainability.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak