Keystroke Dynamics Against Academic Dishonesty in the Age of LLMs

The transition to online examinations and assignments raises significant concerns about academic integrity. Traditional plagiarism detection systems often struggle to identify instances of intelligent cheating, particularly when students utilize advanced generative AI tools to craft their responses. This study proposes a keystroke dynamics-based method to differentiate between bona fide and assisted writing within academic contexts. To facilitate this, a dataset was developed to capture the keystroke patterns of individuals engaged in writing tasks, both with and without the assistance of generative AI. The detector, trained using a modified TypeNet architecture, achieved accuracies ranging from 74.98% to 85.72% in condition-specific scenarios and from 52.24% to 80.54% in condition-agnostic scenarios. The findings highlight significant differences in keystroke dynamics between genuine and assisted writing. The outcomes of this study enhance our understanding of how users interact with generative AI and have implications for improving the reliability of digital educational platforms.

Medical Image Analysis for Detection, Treatment and Planning of Disease using Artificial Intelligence Approaches

X-ray is one of the prevalent image modalities for the detection and diagnosis of the human body. X-ray provides an actual anatomical structure of an organ present with disease or absence of disease. Segmentation of disease in chest X-ray images is essential for the diagnosis and treatment. In this paper, a framework for the segmentation of X-ray images using artificial intelligence techniques has been discussed. Here data has been pre-processed and cleaned followed by segmentation using SegNet and Residual Net approaches to X-ray images. Finally, segmentation has been evaluated using well known metrics like Loss, Dice Coefficient, Jaccard Coefficient, Precision, Recall, Binary Accuracy, and Validation Accuracy. The experimental results reveal that the proposed approach performs better in all respect of well-known parameters with 16 batch size and 50 epochs. The value of validation accuracy, precision, and recall of SegNet and Residual Unet models are 0.9815, 0.9699, 0.9574, and 0.9901, 0.9864, 0.9750 respectively.

supDQN: Supervised Rewarding Strategy Driven Deep Q-Network for sEMG Signal Decontamination

The presence of muscles throughout the active parts of the body such as the upper and lower limbs, makes electromyography-based human-machine interaction prevalent. However, muscle signals are stochastic and noisy. These noises can be regular and irregular. Irregular noises due to movements or electrical switching require dynamic filtering. Conventionally, filters are stacked, which trims and delays the signal unnecessarily. This study introduces a decontamination technique involving a supervised rewarding strategy to drive a deep Q-network-based agent (supDQN). It applies one of three filters to decontaminate a 1sec long surface electromyography signal, which is dynamically contaminated. A machine learning agent identifies whether the signal after filtering is clean or noisy. Accordingly, a reward is generated. The identification accuracy is enhanced by using a local interpretable model-agnostic explanation. The deep Q-network is guided by this reward to select filter optimally while decontaminating a signal. The proposed filtering strategy is tested on four noise levels (-5 dB, -1 dB, +1 dB, +5 dB). supDQN filters the signal desirably when the signal-to-noise ratio (SNR) is between -5 dB to +1 dB. It filters less desirably at high SNR (+5 dB). A normalized root mean square (nRMSE) is formulated to depict the difference of filtered signal from ground truth. This is used to compare supDQN and conventional methods including wavelet denoising with debauchies and symlet wavelet, high order low pass filter, notch filter, and high pass filter. The proposed filtering strategy gives an average value nRMSE of 1.1974, which is lower than the conventional filters.

MEET: Mixture of Experts Extra Tree-Based sEMG Hand Gesture Identification

Artificial intelligence (AI) has made significant advances in recent years and opened up new possibilities in exploring applications in various fields such as biomedical, robotics, education, industry, etc. Among these fields, human hand gesture recognition is a subject of study that has recently emerged as a research interest in robotic hand control using electromyography (EMG). Surface electromyography (sEMG) is a primary technique used in EMG, which is popular due to its non-invasive nature and is used to capture gesture movements using signal acquisition devices placed on the surface of the forearm. Moreover, these signals are pre-processed to extract significant handcrafted features through time and frequency domain analysis. These are helpful and act as input to machine learning (ML) models to identify hand gestures. However, handling multiple classes and biases are major limitations that can affect the performance of an ML model. Therefore, to address this issue, a new mixture of experts extra tree (MEET) model is proposed to identify more accurate and effective hand gesture movements. This model combines individual ML models referred to as experts, each focusing on a minimal class of two. Moreover, a fully trained model known as the gate is employed to weigh the output of individual expert models. This amalgamation of the expert models with the gate model is known as a mixture of experts extra tree (MEET) model. In this study, four subjects with six hand gesture movements have been considered and their identification is evaluated among eleven models, including the MEET classifier. Results elucidate that the MEET classifier performed best among other algorithms and identified hand gesture movement accurately.

Intelligent fault diagnosis of worm gearbox based on adaptive CNN using amended gorilla troop optimization with quantum gate mutation strategy

The worm gearbox is a high-speed transmission system that plays a vital role in various industries. Therefore it becomes necessary to develop a robust fault diagnosis scheme for worm gearbox. Due to advancements in sensor technology, researchers from academia and industries prefer deep learning models for fault diagnosis purposes. The optimal selection of hyperparameters (HPs) of deep learning models plays a significant role in stable performance. Existing methods mainly focused on manual tunning of these parameters, which is a troublesome process and sometimes leads to inaccurate results. Thus, exploring more sophisticated methods to optimize the HPs automatically is important. In this work, a novel optimization, i.e. amended gorilla troop optimization (AGTO), has been proposed to make the convolutional neural network (CNN) adaptive for extracting the features to identify the worm gearbox defects. Initially, the vibration and acoustic signals are converted into 2D images by the Morlet wavelet function. Then, the initial model of CNN is developed by setting hyperparameters. Further, the search space of each Hp is identified and optimized by the developed AGTO algorithm. The classification accuracy has been evaluated by AGTO-CNN, which is further validated by the confusion matrix. The performance of the developed model has also been compared with other models. The AGTO algorithm is examined on twenty-three classical benchmark functions and the Wilcoxon test which demonstrates the effectiveness and dominance of the developed optimization algorithm. The results obtained suggested that the AGTO-CNN has the highest diagnostic accuracy and is stable and robust while diagnosing the worm gearbox.

An Adaptive feature mode decomposition based on a novel health indicator for bearing fault diagnosis

The vibration analysis of the bearing is very crucial because of its non-stationary nature and low signal-to-noise ratio. Therefore, a novel scheme for detecting bearing defects is put forward based on the extraction of single-valued neutrosophic cross-entropy (SVNCE) to address this issue. Initially, the artificial hummingbird algorithm (AHA) is used to make the feature mode decomposition (FMD) adaptive by optimizing its parameter based on a newly developed health indicator (HI) i.e. sparsity impact measure index (SIMI). This HI ensures full sparsity and impact properties simultaneously. The raw signals are disintegrated into different modes by adaptive FMD at optimal values of its parameters. The energy of these modes is calculated for different health conditions. The energy interval range has been decided based on energy eigen which are then transformed into single-valued neutrosophic sets (SVNSs) for unknown defect conditions. The minimum argument principle employs the least SVNCE values between SVNSs of testing samples (obtained from unknown bearing conditions) and SVNSs of training samples (obtained from known bearing conditions) to recognize the different defects in the bearing. It has been discovered that the suggested methodology is more adept at identifying the various bearing defects.

Can LLMs Compute with Reasons?

Large language models (LLMs) often struggle with complex mathematical tasks, prone to "hallucinating" incorrect answers due to their reliance on statistical patterns. This limitation is further amplified in average Small LangSLMs with limited context and training data. To address this challenge, we propose an "Inductive Learning" approach utilizing a distributed network of SLMs. This network leverages error-based learning and hint incorporation to refine the reasoning capabilities of SLMs. Our goal is to provide a framework that empowers SLMs to approach the level of logic-based applications achieved by high-parameter models, potentially benefiting any language model. Ultimately, this novel concept paves the way for bridging the logical gap between humans and LLMs across various fields.

Deep Generative Attacks and Countermeasures for Data-Driven Offline Signature Verification

While previous studies have explored attacks via random, simple, and skilled forgeries, generative attacks have received limited attention in the data-driven signature verification (DASV) process. Thus, this paper explores the impact of generative attacks on DASV and proposes practical and interpretable countermeasures. We investigate the power of two prominent Deep Generative Models (DGMs), Variational Auto-encoders (VAE) and Conditional Generative Adversarial Networks (CGAN), on their ability to generate signatures that would successfully deceive DASV. Additionally, we evaluate the quality of generated images using the Structural Similarity Index measure (SSIM) and use the same to explain the attack's success. Finally, we propose countermeasures that effectively reduce the impact of deep generative attacks on DASV. We first generated six synthetic datasets from three benchmark offline-signature datasets viz. CEDAR, BHSig260- Bengali, and BHSig260-Hindi using VAE and CGAN. Then, we built baseline DASVs using Xception, ResNet152V2, and DenseNet201. These DASVs achieved average (over the three datasets) False Accept Rates (FARs) of 2.55%, 3.17%, and 1.06%, respectively. Then, we attacked these baselines using the synthetic datasets. The VAE-generated signatures increased average FARs to 10.4%, 10.1%, and 7.5%, while CGAN-generated signatures to 32.5%, 30%, and 26.1%. The variation in the effectiveness of attack for VAE and CGAN was investigated further and explained by a strong (rho = -0.86) negative correlation between FARs and SSIMs. We created another set of synthetic datasets and used the same to retrain the DASVs. The retained baseline showed significant robustness to random, skilled, and generative attacks as the FARs shrank to less than 1% on average. The findings underscore the importance of studying generative attacks and potential countermeasures for DASV.

Dictionary Attack on IMU-based Gait Authentication

We present a novel adversarial model for authentication systems that use gait patterns recorded by the inertial measurement unit (IMU) built into smartphones. The attack idea is inspired by and named after the concept of a dictionary attack on knowledge (PIN or password) based authentication systems. In particular, this work investigates whether it is possible to build a dictionary of IMUGait patterns and use it to launch an attack or find an imitator who can actively reproduce IMUGait patterns that match the target's IMUGait pattern. Nine physically and demographically diverse individuals walked at various levels of four predefined controllable and adaptable gait factors (speed, step length, step width, and thigh-lift), producing 178 unique IMUGait patterns. Each pattern attacked a wide variety of user authentication models. The deeper analysis of error rates (before and after the attack) challenges the belief that authentication systems based on IMUGait patterns are the most difficult to spoof; further research is needed on adversarial models and associated countermeasures.

Synthesizing Human Gaze Feedback for Improved NLP Performance

Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human cognitive signals in the form of eyetracking). Prior eye tracking and NLP research reveal that cognitive processes, such as human scanpaths, gleaned from human gaze patterns aid in the understanding and performance of NLP models. However, the collection of real eyetracking data for NLP tasks is challenging due to the requirement of expensive and precise equipment coupled with privacy invasion issues. To address this challenge, we propose ScanTextGAN, a novel model for generating human scanpaths over text. We show that ScanTextGAN-generated scanpaths can approximate meaningful cognitive signals in human gaze patterns. We include synthetically generated scanpaths in four popular NLP tasks spanning six different datasets as proof of concept and show that the models augmented with generated scanpaths improve the performance of all downstream NLP tasks.