Technocrats Institute of Technology

With the rapid growth and diversification of malware, accurate multi-class detection remains challenging due to severe class imbalance and limited labeled data. This work presents an image-based malware classification framework that converts executable binaries into 64×64 grayscale images, employs class-wise DCGAN augmentation to mitigate severe imbalance (initial imbalance ratio >12 across 31 families, N≈9300), and trains a hybrid CNN–Transformer model that captures both local texture features and long-range contextual dependencies. The DCGAN generator produces high-fidelity synthetic samples, evaluated using Inception Score (IS) =3.43, Fréchet Inception Distance (FID) =10.99, and Kernel Inception Distance (KID) =0.0022, and is used to equalize class counts before classifier training. On the blended dataset the proposed GAN-balanced CNN–Transformer achieves an overall accuracy of 95% and a macro-averaged F1-score of 0.95; the hybrid model also attains validation accuracy of ≈94% while substantially improving minority-class recognition. Compared to CNN-only and Transformer-only baselines, the hybrid approach yields more stable convergence, reduced overfitting, and stronger per-class performance, while remaining feasible for practical deployment. These results demonstrate that DCGAN-driven balancing combined with CNN–Transformer feature fusion is an effective, scalable solution for robust malware family classification.

Modern society faces serious energy challenges, including the depletion of fossil fuels, environmental degradation, and global climate change. These pressing issues underscore the urgent need for sustainable energy storage and conversion technologies. In this context, carbon foam (CF) functionalized with ZnO nanorods (NRs) shows significant promise. To fabricate the carbon foam, a polyurethane (PU) foam template was used along with phenolic resin as the carbon source. The structure was stabilized by oxidation and then sintered at 1000 degrees C under a nitrogen atmosphere. ZnO NRs were subsequently grown on the CF using an in situ hydrothermal method, with loading concentrations ranging from 0 to 10 wt%. The structural and morphological characteristics of the ZnO NRs-functionalized CFs were analysed using XRD, SEM, and Raman spectroscopy. The SEM results revealed that ZnO were uniformly distributed across the CF surface. The electrochemical characteristics of binder-free electrodes based on ZnO NRs-functionalized CFs were systematically examined using cyclic voltammetry (CV), electrochemical impedance spectroscopy (EIS), and galvanostatic charge-discharge (GCD) measurements. In a three-electrode system, the CF electrode functionalized with 10 wt% ZnO NRs exhibited a remarkable specific capacitance of 360 F g-1 at a scan rate of 5 mV s-1. Furthermore, an asymmetric supercapacitor device was assembled using the 10 wt% ZnO NRs-functionalized CF as the positive electrode and pristine CF as the negative electrode (denoted as CF-ZnO-10//CF). This device demonstrated excellent electrochemical performance, delivering a specific capacitance of 272 F g-1 at a current density of 0.5 A g-1, together with an energy density of 38 Wh kg-1 and a power density of 125 W kg-1. These results confirm the strong potential of ZnO NRs functionalized CF as a high-performance, binder-free electrode material for next-generation supercapacitor applications.

Images captured underwater have a high tendency of degradation, such as color, poor contrast, blur, and loss of detail, because of light absorption and scattering mechanisms in an underwater environment. A novel single-image restoration approach is proposed to resolve these challenges using state-of-the-art machine learning methods. The hybrid architecture combines transformer-based attention with domain-specific pri-ors to improve both visual and quantitative scores. This research evaluates Phase Former and UniUIR techniques in real-life and synthetic data. We observe stable improvements over other state-of-the-art techniques. This proposed framework consistently achieves superior performance without depending on different circumstances in terms of both visual quality and quantitative evaluation metrics. We have found improvements in PSNR, SSIM, UCIQE, and UIQM in the quantitative test. The analysis of the visual results showed clearer textures and more natural color adjustments in underwater image restoration, but the failure case analysis indicates obstacles in extremely turbid scenes. The suggested method performs well in most state-of-the-art algorithms and also offers some progress in practicality. Future studies will emphasize multimodal sensor integration and real-time underwater embedded systems applications.

Phishing detectors can achieve high benchmark accuracy while remaining vulnerable to feature manipulation and difficult to assess as trustworthy decision systems; this study evaluates leakage controlled discrimination calibration explanation stability and constrained adversarial robustness on the PhiUSIIL dataset through a normalized domain grouped development protocol and one frozen test assessment; five model families were compared under conservative and full sensitivity feature conditions while calibration permutation importance Tree SHAP explanations and greedy feature space evasion were analysed; conservative uncalibrated HistGradientBoosting achieved locked test recall of 0.999897 F1 of 0.999949 and Brier score of 0.000041 although attack success reached 0.7042 at three changes and 0.8462 at five changes while mean SHAP cosine similarity fell to minus 0.350; the study also presents a six layer operational architecture that connects evidence governance prediction explanation robustness controls and monitoring; the evidence shows that clean grouped performance and probability reliability can coexist with severe representation level vulnerability and therefore phishing model evaluation should report predictive calibration explanation architectural and adversarial evidence together.

Automated dermoscopic classification can support skin lesion assessment while reliable research requires leakage safe partitions class sensitive evaluation calibrated confidence interpretable predictions and practical computational cost; therefore this work presents MedLite XAI which combines a MobileNetV3 Small image encoder with patient metadata for seven class classification on HAM10000; a deterministic lesion grouped split allocated 7012 training images 1502 validation images and 1501 locked test images while model selection used validation macro F1 only; the selected metadata aware cross entropy model obtained 74.65 percent validation macro F1 and achieved 84.08 percent accuracy 71.59 percent macro F1 and 71.34 percent balanced accuracy on the final test set; temperature scaling reduced expected calibration error from 6.69 percent to 2.09 percent while preserving class predictions and Grad CAM analysis across 20 validation cases produced mean horizontal flip stability of 0.969; consequently MedLite XAI provides a reproducible lightweight research framework although external and prospective clinical validation remain necessary.