Search Results (538)

Recent advancements in cyber threats have led to increasingly sophisticated attack methods that evade traditional malware detection systems. In-memory malware, a particularly challenging variant, operates by modifying volatile memory, leaving minimal traces on secondary storage. This paper presents an in-depth analysis of in-memory malware characteristics, behavior, and evasion strategies. We propose “MemCatcher”, a novel detection algorithm that integrates real-time system activity monitoring and memory analysis to effectively identify these threats from the Windows 10 system. Experimental validation using real-world and synthetic in-memory malware samples demonstrates the effectiveness of our approach. Additionally, we analyze evasion tactics using “Volatility3” and “PEview”, providing insights into countermeasures. Future work will focus on enhancing in-memory malware detection using “Processor-in-Memory (PIM) hardware”. Full article

Memory forensics is an essential cybersecurity tool that comprehensively examines volatile memory to detect the malicious activity of fileless malware that can bypass disk analysis. Image-based detection techniques provide a promising solution by visualizing memory data into images to be used and analyzed by image processing tools and machine learning methods. However, the effectiveness of image-based data for detection and classification requires high computational efforts. This paper investigates the efficacy of texture-based methods in detecting and classifying memory-resident or fileless malware using different image resolutions, identifying the best feature descriptors, classifiers, and resolutions that accurately classify malware into specific families and differentiate them from benign software. Moreover, this paper uses both local and global descriptors, where local descriptors include Oriented FAST and Rotated BRIEF (ORB), Scale-Invariant Feature Transform (SIFT), and Histogram of Oriented Gradients (HOG) and global descriptors include Discrete Wavelet Transform (DWT), GIST, and Gray Level Co-occurrence Matrix (GLCM). The results indicate that as image resolution increases, most feature descriptors yield more discriminative features but require higher computational efforts in terms of time and processing resources. To address this challenge, this paper proposes a novel approach that integrates Local Interpretable Model-agnostic Explanations (LIME) with deep learning models to automatically identify and crop the most important regions of memory images. The LIME’s ROI was extracted based on ResNet50 and MobileNet models’ predictions separately, the images were resized to 128 × 128, and the sampling process was performed dynamically to speed up LIME computation. The ROIs of the images are cropped to new images with sizes of (100 × 100) in two stages: the coarse stage and the fine stage. The two generated LIME-based cropped images using ResNet50 and MobileNet are fed to the lightweight neural network to evaluate the effectiveness of the LIME-based identified regions. The results demonstrate that the LIME-based MobileNet model’s prediction improves the efficiency of the model by preserving important features with a classification accuracy of 85% on multi-class classification. Full article

Image convolution is a commonly required task in machine vision and Convolution Neural Networks (CNNs). Due to the large data movement required, image convolution can benefit greatly from in-memory computing. However, image convolution is very computationally intensive, requiring ${(n-(k-1))}^2$ Inner Product (IP) computations for convolution of a $n\times n$ image with a $k\times k$ kernel. For example, for a convolution of a 224 × 224 image with a 3 × 3 kernel, 49,284 IPs need to be computed, where each IP requires nine multiplications and eight additions. This is a major hurdle for in-memory implementation because in-memory adders and multipliers are extremely slow compared to CMOS multipliers. In this work, we revive an old technique called ‘Distributed Arithmetic’ and judiciously apply it to perform image convolution in memory without area-intensive hard-wired multipliers. Distributed arithmetic performs multiplication using shift-and-add operations, and they are implemented using CMOS circuits in the periphery of ReRAM memory. Compared to Google’s TPU, our in-memory architecture requires 56× less energy while incurring 24× more latency for convolution of a 224 × 224 image with a 3 × 3 filter. Full article

As a core clean energy source in the global energy transition, natural gas price fluctuations directly affect the energy market supply demand balance, industrial chain cost control, etc. Thus, accurate natural gas price prediction is crucial for market participants’ decision making and policymakers’ regulation. To tackle the issue that traditional single models fail to capture data patterns of the New York Mercantile Exchange (NYMEX) natural gas futures daily prices—due to their nonlinearity, high volatility, and multi-scale features—this study proposes a hybrid model: VMD-CNN-BiLSTM-attention, integrating Variational Mode Decomposition (VMD), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and an attention mechanism. A one-step to four-step forecasting comparison was conducted using NYMEX natural gas futures daily closing prices, with the proposed model vs. CNN-BiLSTM-Attention and Autoregressive Integrated Moving Average (ARIMA) models. The empirical results show that the VMD-CNN-BiLSTM-attention model outperforms the comparison models in terms of Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), etc. Specifically, its four-step forecast MAPE stays ≤3.5% and $R^2$ ≥ 98%, demonstrating a stronger ability to capture complex price fluctuations, better accuracy, and stability than traditional single models and deep learning models without VMD, and provides reliable technical support for short-to-medium-term natural gas price prediction. Full article

In the pursuit of advanced non-volatile memory technologies, ferroelectric memristors have attracted great attention. However, traditional perovskite ferroelectric materials are hampered by environmental pollution, limited applicability, and the complexity and high cost of conventional vacuum deposition methods. This has spurred the exploration of alternative materials and fabrication strategies. Herein, a flexible Pt/Zr: HfO₂ (HZO)/graphene oxide (GO)/mica memristor is successfully fabricated using the total solution-processed method. The interfacial oxygen competition mechanism between the HZO layer and the GO bottom electrode facilitates the formation of the HZO ferroelectric phase. The as-prepared device exhibits a switching ratio of approximately 150 and can maintain eight distinct resistance levels, and it can also effectively simulate neural responses. By integrating the ferroelectric polarization principle and the piezoelectric effect of HZO, along with the influence of GO, the performance variations of the as-prepared device under mechanical and thermal influences are further explored. Notably, Morse code recognition is achieved by utilizing the device’s pressure properties and setting specific press rules. The as-prepared device can accurately convert and store information, opening new avenues for non-volatile memory applications in silent communication and promoting the development of wearable electronics. Full article

The global pursuit of sustainable development amplifies renewable energy’s strategic importance, positioning wind power as a vital modern grid component. Accurate wind forecasting is essential to counter inherent volatility, enabling robust grid operations, security protocols, and optimization strategies. Such predictive precision directly governs wind energy systems’ stability and sustainability. This research introduces a novel spatio-temporal hybrid model integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and graph convolutional networks (GCN) to extract temporal patterns and meteorological dynamics (wind speed, direction, temperature) across 134 wind turbines. Building upon conventional methods, our architecture captures turbine spatio-temporal correlations while assimilating multivariate meteorological characteristics. Addressing data integrity compromises from equipment failures and extreme weather-which undermine data-driven models-we implement Wasserstein GAN (WGAN) for generative missing-value interpolation. Validation across severe data loss scenarios (30–90% missing values) demonstrates the model’s enhanced predictive capacity. Rigorous benchmarking confirms significant accuracy improvements and reduced forecasting errors. Full article

The Hurst parameter H plays a critical role in modeling long-memory behavior in financial time series, particularly within the framework of the fractional Black–Scholes model (fBSM). While the Method of Moments (MOM) provides a fast, closed-form estimator for H, it suffers from increasing negative bias, especially as H grows beyond 0.6. This paper proposes a bias-corrected version of the MOM estimator based on a quadratic regression fit derived from simulation data. The corrected estimator substantially reduces estimation error while retaining computational efficiency. Through extensive simulations, we quantify the impact of MOM bias on option pricing and demonstrate how our correction method leads to more accurate pricing under the fBSM. We apply the methodology to real financial assets—including Natural Gas, Apple, Gold, and Crude Oil—and show that the corrected Hurst estimates reduce option pricing error by up to USD 0.47 per contract relative to the uncorrected estimator, depending on the asset’s volatility structure. These results underscore the importance of accurate Hurst parameter estimation for derivative pricing, particularly in volatile markets such as energy and commodities, while also remaining relevant to equities and precious metals. The corrected estimator thus offers practitioners a simple yet effective tool to improve financial decision-making. Full article

Because of the inherent volatility and non-linearity of financial markets, precise forecasting is a constant struggle. Using historical data, this study examines how well intelligent algorithms in forecast trading market trends. It contrasts a number of machine learning methods, such as Random Forest, K-Nearest Neighbors (KNN), XGBoost, and Decision Tree, with a deep learning methodology based on Long Short-Term Memory (LSTM) networks. It is possible to assess these models’ capacity to identify intricate temporal patterns because they are trained directly on historical price data rather than using specially designed technical indicators. The findings provide insights into successful data-driven forecasting techniques by highlighting the advantages and disadvantages of each approach in various market scenarios. Supporting the creation of predictive tools for well-informed decision-making in trading environments is the goal of this research. Full article

As an emerging type of non-volatile memory, magneto-resistive random access memory (MRAM) stands out for its exceptional reliability and rapid read–write speeds, thereby garnering considerable attention within the industry. The memory cell architecture of MRAM is centered around the magnetic tunnel junction (MTJ), which, however, is prone to interference from external magnetic fields—a limitation that restricts its application in demanding environments. To address this challenge, we propose an innovative open magnetic shielding structure. This design demonstrates remarkable shielding efficacy against both in-plane and perpendicular magnetic fields, effectively catering to the magnetic shielding demands of both spin-transfer torque (STT) and spin–orbit torque (SOT) MRAM. Finite element magnetic simulations reveal that when subjected to an in-plane magnetic field of 40 mT, the magnetic field intensity at the chip level is reduced to nearly 1‰ of its original value. Similarly, under a perpendicular magnetic field of 40 mT, the magnetic field at the chip is reduced to 2‰ of its initial strength. Such reductions significantly enhance the anti-magnetic capabilities of MRAM. Moreover, the magnetic shielding performance remains unaffected by the height of the packaging structure, ensuring compatibility with various chip stack packaging requirements across different layers. The research presented in this paper holds immense significance for the realization of highly reliable magnetic shielding packaging solutions for MRAM. Full article

Bitcoin’s extreme price volatility presents significant challenges for investors and traders, necessitating accurate predictive models to guide decision-making in cryptocurrency markets. This study compares the performance of machine learning approaches for Bitcoin price prediction, specifically examining XGBoost gradient boosting, Long Short-Term Memory (LSTM), and GARCH-DL neural networks using comprehensive market data spanning December 2013 to May 2025. We employed extensive feature engineering incorporating technical indicators, applied multiple machine and deep learning models configurations including standalone and ensemble approaches, and utilized cross-validation techniques to assess model robustness. Based on the empirical results, the most significant practical implication is that traders and financial institutions should adopt a dual-model approach, deploying XGBoost for directional trading strategies and utilizing LSTM models for applications requiring precise magnitude predictions, due to their superior continuous forecasting performance. This research demonstrates that traditional technical indicators, particularly market capitalization and price extremes, remain highly predictive in algorithmic trading contexts, validating their continued integration into modern cryptocurrency prediction systems. For risk management applications, the attention-based LSTM’s superior risk-adjusted returns, combined with enhanced interpretability, make it particularly valuable for institutional portfolio optimization and regulatory compliance requirements. The findings suggest that ensemble methods offer balanced performance across multiple evaluation criteria, providing a robust foundation for production trading systems where consistent performance is more valuable than optimization for single metrics. These results enable practitioners to make evidence-based decisions about model selection based on their specific trading objectives, whether focused on directional accuracy for signal generation or precision of magnitude for risk assessment and portfolio management. Full article

The prediction of stock prices is challenging due to their volatility, irregular patterns, and complex time-series structure. Reliably forecasting stock market data plays a crucial role in minimizing financial risk and optimizing investment strategies. However, traditional models often struggle to capture temporal dependencies and extract relevant features from noisy inputs, which limits their predictive performance. To improve this, we developed an enhanced recursive feature elimination (RFE) method that blends the importance of impurity-based features from random forest and gradient boosting models with Kendall tau correlation analysis, and we applied SHapley Additive exPlanations (SHAP) analysis to externally validate the reliability of the selected features. This approach leads to more consistent and reliable feature selection for short-term stock prediction over 1-, 3-, and 7-day intervals. The proposed deep learning (DL) architecture integrates a temporal convolutional network (TCN) for long-term pattern recognition, a gated recurrent unit (GRU) for sequence capture, and multi-head attention (MHA) for focusing on critical information, thereby achieving superior predictive performance. We evaluate the proposed approach using daily stock price data from three leading companies—HDFC Bank, Tata Consultancy Services (TCS), and Tesla—and two major stock indices: Nifty 50 and S&P 500. The performance of our model is compared against five benchmark models: temporal convolutional network (TCN), long short-term memory (LSTM), GRU, Bidirectional GRU, and a hybrid TCN–GRU model. Our method consistently shows lower error rates and higher predictive accuracy across all datasets, as measured by four commonly used performance metrics. Full article

Global enterprises face increasingly volatile market conditions, with foreign exchange (FX) movements often forcing executives to make rapid pricing and strategy decisions under uncertainty. While artificial intelligence (AI) has transformed operational decision-making, its role in supporting board-level strategic choices remains underexplored. This paper examines how AI and advanced analytics can serve as a ‘decision companion’ for management teams and executives confronted with global shocks. Using Roblox Corporation as a case study, we apply a Long Short-Term Memory (LSTM) neural network to forecast bookings and simulate counterfactual scenarios involving euro depreciation and European price adjustments. The analysis reveals that a ten percent depreciation of the euro reduces consolidated bookings and profits by approximately six percent, and that raising European prices does not offset these losses due to demand elasticity. Regional attribution shows that the majority of the decline is concentrated in Europe, with only minor spillovers elsewhere. The findings demonstrate that AI enhances strategic agility by clarifying risks, quantifying trade-offs, and isolating regional effects, while ensuring that ultimate decisions remain with human executives. Full article

The rapid growth of data-intensive applications has imposed significant demands on the performance of distributed file systems, particularly in metadata operations. Traditional systems rely heavily on metadata servers to handle indexing tasks, leading to Central Processing Unit (CPU) bottlenecks and increased latency. To address these challenges, we propose Direct File System (DirectFS), an Remote Direct Memory Access (RDMA)-accelerated distributed file system that offloads metadata indexing to clients by leveraging one-sided RDMA operations. Further, we propose a range of techniques, including hash-based namespace indexing and hotness-aware metadata prefetching, to fully unleash the performance potential of RDMA hardware. We implement DirectFS on top of Moose File System (MooseFS) and compare DirectFS with state-of-the-art distributed file systems using a variety of Filebench v1.4.9.1 and MDTest from the IOR suite v4.0.0 workloads. Evaluation results demonstrate that DirectFS achieves significant performance improvements for metadata-intensive benchmarks compared to other file systems. Full article

This study introduces and evaluates stochastic models to describe Bitcoin price dynamics at different time scales, using daily data from January 2019 to December 2024 and intraday data from 20 January 2025. In the daily analysis, models based on are introduced to capture long memory, paired with both constant-volatility (CONST) and stochastic-volatility specifications via the Cox–Ingersoll–Ross (CIR) process. The novel family of models is based on Generalized Ornstein–Uhlenbeck processes with a fluctuating exponential trend (GOU-FE), which are modified to account for multiplicative fBm noise. Traditional Geometric Brownian Motion processes (GFBM) with either constant or stochastic volatilities are employed as benchmarks for comparative analysis, bringing the total number of evaluated models to four: GFBM-CONST, GFBM-CIR, GOUFE-CONST, and GOUFE-CIR models. Estimation by numerical optimization and evaluation through error metrics, information criteria (AIC, BIC, and EDC), and 95% Expected Shortfall (ES₉₅) indicated better fit for the stochastic-volatility models (GOUFE-CIR and GFBM-CIR) and the lowest tail-risk for GOUFE-CIR, although residual analysis revealed heteroscedasticity and non-normality. For intraday data, Exponential, Weibull, and Generalized Gamma Autoregressive Conditional Duration (ACD) models, with adjustments for intraday patterns, were applied to model the time between transactions. Results showed that the ACD models effectively capture duration clustering, with the Generalized Gamma version exhibiting superior fit according to the Cox–Snell residual-based analysis and other metrics (AIC, BIC, and mean-squared error). Overall, this work advances the modeling of Bitcoin prices by rigorously applying and comparing stochastic frameworks across temporal scales, highlighting the critical roles of long memory, stochastic volatility, and intraday dynamics in understanding the behavior of this digital asset. Full article

The rapid growth of artificial intelligence (AI), data centers, and high-performance computing (HPC) has increased the demand for large bandwidth, high energy efficiency, and high-density optical interconnects. Co-packaged optics (CPO) technology offers a promising solution by integrating photonic integrated circuits (PICs) directly within or close to electronic integrated circuit (EIC) packages. This paper explores the evolution of CPO performance from various perspectives, including fan-out wafer level packaging (FOWLP), through-silicon via (TSV)-based packaging, through-glass via (TGV)-based packaging, femtosecond laser direct writing waveguides, ion-exchange glass waveguides, and optical coupling. Micro ring resonators (MRRs) are a high-density integration solution due to their compact size, excellent energy efficiency, and compatibility with CMOS processes. However, traditional thermal tuning methods face limitations such as high static power consumption and severe thermal crosstalk. To address these issues, non-volatile neuromorphic photonics has made breakthroughs using phase-change materials (PCMs). By combining the integrated storage and computing capabilities of photonic memory with the efficient optoelectronic interconnects of CPO, this deep integration is expected to work synergistically to overcome material, integration, and architectural challenges, driving the development of a new generation of computing hardware with high energy efficiency, low latency, and large bandwidth. Full article