This paper presents NeutroSENSE, a neutrosophic-enhanced ensemble framework for interpretable intrusion detection in IoT environments. By integrating Random Forest, XGBoost, and Logistic Regression with neutrosophic logic, the system decomposes prediction confidence into truth (T), falsity (F), and indeterminacy (I) components, enabling uncertainty quantification and abstention. Predictions with high indeterminacy are flagged for review using both global and adaptive, class-specific thresholds. Evaluated on the IoT-CAD dataset, NeutroSENSE achieved 97% accuracy, while demonstrating that misclassified samples exhibit significantly higher indeterminacy (I = 0.62) than correct ones (I = 0.24). The use of indeterminacy as a proxy for uncertainty enables informed abstention and targeted review-particularly valuable in edge deployments. Figures and tables validate the correlation between I-scores and error likelihood, supporting more trustworthy, human-in-the-loop AI decisions. This work shows that neutrosophic logic enhances both accuracy and explainability, providing a practical foundation for trust-aware AI in edge and fog-based IoT security systems.

Current methods largely rely on subjective observation and rating, which introduce variability and bias, lack physiological grounding, and do not generalize across tasks or individuals . While functional near - infrared spectroscopy (fNIRS) has emerged as a promising non - invasive tool for measuring neural activity during task performance [Nemani et al., 2018; Gao et al., 2021; Keles et al., 2021], prior models -- including our own -- have largely relied on extensive preprocessing pipelines, lacked physiological interpretability, and demonstrated limited generalization across tasks or stress conditions . Recent sub - region - based analyses have shown that localized activation patterns in prefrontal and motor - related areas can distinguish between proficient and non - proficient performers [Nemani et al., 2018, Gao et al., 2021, Subedi et al., 2025]. The complex spatiotemporal dynamics captured in these signals contain rich information about cognitive and motor processes that could enable more robust, generalizable assessments across diverse settings. However, existing models tend to be task - specific and require retraining when applied to new procedures, impeding scalability . These limitations highlight the need for a domain - specific foundation model -- an architecture trained to extract reusable neural representations across various tasks, individuals, and conditions. In contrast to conventional pipelines, such a model would support modular adaptation to new contexts using minimal data, while retaining interpretability. Foundation models, initially developed in natural language processing and vision [ Lu et.

In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns over potential misuse. Consequently, some academic endeavors have sought to introduce watermarking techniques, characterized by the inclusion of markers within machine-generated text, to facilitate algorithmic identification. This research project is focused on the development of a novel methodology for the detection of synthetic text, with the overarching goal of ensuring the ethical application of LLMs in AI-driven text generation. The investigation commences with replicating findings from a previous baseline study, thereby underscoring its susceptibility to variations in the underlying generation model. Subsequently, we propose an innovative watermarking approach and subject it to rigorous evaluation, employing paraphrased generated text to asses its robustness. Experimental results highlight the robustness of our proposal compared to the~\cite{aarson} watermarking method.

Forecasting central bank policy decisions remains a persistent challenge for investors, financial institutions, and policymakers due to the wide-reaching impact of monetary actions. In particular, anticipating shifts in the U.S. federal funds rate is vital for risk management and trading strategies. Traditional methods relying only on structured macroeconomic indicators often fall short in capturing the forward-looking cues embedded in central bank communications. This study examines whether predictive accuracy can be enhanced by integrating structured data with unstructured textual signals from Federal Reserve communications. We adopt a multi-modal framework, comparing traditional machine learning models, transformer-based language models, and deep learning architectures in both unimodal and hybrid settings. Our results show that hybrid models consistently outperform unimodal baselines. The best performance is achieved by combining TF-IDF features of FOMC texts with economic indicators in an XGBoost classifier, reaching a test AUC of 0.83. FinBERT-based sentiment features marginally improve ranking but perform worse in classification, especially under class imbalance. SHAP analysis reveals that sparse, interpretable features align more closely with policy-relevant signals. These findings underscore the importance of integrating textual and structured signals transparently. For monetary policy forecasting, simpler hybrid models can offer both accuracy and interpretability, delivering actionable insights for researchers and decision-makers.

Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing its effect on individual outputs is still lacking. Here, we propose a new method for measuring the contribution that fine-tuning makes to individual LLM responses, assuming access to the original pre-trained model. Our method tracks the model's intermediate hidden states, providing a more fine-grained insight into the effects of fine-tuning than a simple comparison of final outputs from pre-trained and fine-tuned models. We introduce and theoretically analyze an exact decomposition of any fine-tuned LLM into a pre-training component and a fine-tuning component. Empirically, we find that model behavior and performance can be steered by up- or down-scaling the fine-tuning component during the forward pass. Motivated by this finding and our theoretical analysis, we define the Tuning Contribution (TuCo) as the ratio of the magnitudes of the fine-tuning component to the pre-training component. We observe that three prominent adversarial attacks on LLMs circumvent safety measures in a way that reduces TuCo, and that TuCo is consistently lower on prompts where these attacks succeed compared to those where they do not. This suggests that attenuating the effect of fine-tuning on model outputs plays a role in the success of such attacks. In summary, TuCo enables the quantitative study of how fine-tuning influences model behavior and safety, and vice versa.

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We evaluate three jailbreaking strategies, including the original AutoDefense attack and two from Deepleaps: BetterDan and JB. Reproducing the AutoDefense framework, we compare single-agent setups with two- and three-agent configurations. Our results show that multi-agent systems enhance resistance to jailbreaks, especially by reducing false negatives. However, its effectiveness varies by attack type, and it introduces trade-offs such as increased false positives and computational overhead. These findings point to the limitations of current automated defences and suggest directions for improving alignment robustness in future LLM systems.

Accurate recognition of Emergency Vehicle (EV) sirens is critical for the integration of intelligent transportation systems, smart city monitoring systems, and autonomous driving technologies. Modern automatic solutions are limited by the lack of large scale, curated datasets and by the computational demands of state of the art sound event detection models. This work introduces E2PANNs (Efficient Emergency Pre trained Audio Neural Networks), a lightweight Convolutional Neural Network architecture derived from the PANNs framework, specifically optimized for binary EV siren detection. Leveraging our dedicated subset of AudioSet (AudioSet EV) we fine-tune and evaluate E2PANNs across multiple reference datasets and test its viability on embedded hardware. The experimental campaign includes ablation studies, cross-domain benchmarking, and real-time inference deployment on edge device. Interpretability analyses exploiting Guided Backpropagation and ScoreCAM algorithms provide insights into the model internal representations and validate its ability to capture distinct spectrotemporal patterns associated with different types of EV sirens. Real time performance is assessed through frame wise and event based detection metrics, as well as a detailed analysis of false positive activations. Results demonstrate that E2PANNs establish a new state of the art in this research domain, with high computational efficiency, and suitability for edge-based audio monitoring and safety-critical applications.

Image generative models have become increasingly popular, but training them requires large datasets that are costly to collect and curate. T o circumvent these costs, some parties may exploit existing models by using the generated images as training data for their own models. In general, watermarking is a valuable tool for detecting unauthorized use of generated images. However, when these images are used to train a new model, watermarking can only enable detection if the watermark persists through training and remains identifiable in the outputs of the newly trained model--a property known as radioactivity. W e analyze the radioactivity of watermarks in images generated by diffusion models (DMs) and image autoregressive models (IARs). W e find that existing watermarking methods for DMs fail to retain radioactivity, as watermarks are either erased during encoding into the latent space or lost in the noising-denoising process (during the training in the latent space). Meanwhile, despite IARs having recently surpassed DMs in image generation quality and efficiency, no radioactive watermarking methods have been proposed for them. T o overcome this limitation, we propose the first watermarking method tailored for IARs and with radioactivity in mind--drawing inspiration from techniques in large language models (LLMs), which share IARs' autoregres-sive paradigm. Our extensive experimental evaluation highlights our method's effectiveness in preserving radioactivity within IARs, enabling robust provenance tracking, and preventing unauthorized use of their generated images.

Spike sorting is a crucial step in decoding multichannel extracellular neural signals, enabling the identification of individual neuronal activity. A key challenge in brain-machine interfaces (BMIs) is achieving real-time, low-power spike sorting at the edge while keeping high neural decoding performance. This study introduces the Neuromorphic Sparse Sorter (NSS), a compact two-layer spiking neural network optimized for efficient spike sorting. NSS leverages the Locally Competitive Algorithm (LCA) for sparse coding to extract relevant features from noisy events with reduced computational demands. NSS learns to sort detected spike waveforms in an online fashion and operates entirely unsupervised. To exploit multi-bit spike coding capabilities of neuromorphic platforms like Intel's Loihi 2, a custom neuron model was implemented, enabling flexible power-performance trade-offs via adjustable spike bit-widths. Evaluations on simulated and real-world tetrode signals with biological drift showed NSS outperformed established pipelines such as WaveClus3 and PCA+KMeans. With 2-bit graded spikes, NSS on Loihi 2 outperformed NSS implemented with leaky integrate-and-fire neuron and achieved an F1-score of 77% (+10% improvement) while consuming 8.6mW (+1.65mW) when tested on a drifting recording, with a computational processing time of 0.25ms (+60 us) per inference.

As the use of AI tools by students has become more prevalent, instructors have started using AI detection tools like GPTZero and QuillBot to detect AI written text. However, the reliability of these detectors remains uncertain. In our study, we focused mostly on the success rate of GPTZero, the most-used AI detector, in identifying AI-generated texts based on different lengths of randomly submitted essays: short (40-100 word count), medium (100-350 word count), and long (350-800 word count). We gathered a data set consisting of twenty-eight AI-generated papers and fifty human-written papers. With this randomized essay data, papers were individually plugged into GPTZero and measured for percentage of AI generation and confidence. A vast majority of the AI-generated papers were detected accurately (ranging from 91-100% AI believed generation), while the human generated essays fluctuated; there were a handful of false positives. These findings suggest that although GPTZero is effective at detecting purely AI-generated content, its reliability in distinguishing human-authored texts is limited. Educators should therefore exercise caution when relying solely on AI detection tools.