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.

This work addresses the challenge of malware classification using machine learning by developing a novel dataset labeled at both the malware type and family levels. Raw binaries were collected from sources such as VirusShare, VX Underground, and MalwareBazaar, and subsequently labeled with family information parsed from binary names and type-level labels integrated from ClarAVy. The dataset includes 14 malware types and 17 malware families, and was processed using a unified feature extraction pipeline based on static analysis, particularly extracting features from Portable Executable headers, to support advanced classification tasks. The evaluation was focused on three key classification tasks. In the binary classification of malware versus benign samples, Random Forest and XGBoost achieved high accuracy on the full datasets, reaching 98.5% for type-based detection and 98.98% for family-based detection. When using truncated datasets of 1,000 samples to assess performance under limited data conditions, both models still performed strongly, achieving 97.6% for type-based detection and 98.66% for family-based detection. For interclass classification, which distinguishes between malware types or families, the models reached up to 97.5% accuracy on type-level tasks and up to 93.7% on family-level tasks. In the multiclass classification setting, which assigns samples to the correct type or family, SVM achieved 81.1% accuracy on type labels, while Random Forest and XGBoost reached approximately 73.4% on family labels. The results highlight practical trade-offs between accuracy and computational cost, and demonstrate that labeling at both the type and family levels enables more fine-grained and insightful malware classification. The work establishes a robust foundation for future research on advanced malware detection and classification.

The opacity of many supervised learning algorithms remains a key challenge, hindering scientific discovery and limiting broader deployment -- particularly in high-stakes domains. This paper develops model- and distribution-agnostic significance tests to assess the influence of input features in any regression or classification algorithm. Our method evaluates a feature's incremental contribution to model performance by masking its values across samples. Under the null hypothesis, the distribution of performance differences across a test set has a non-positive median. We construct a uniformly most powerful, randomized sign test for this median, yielding exact p-values for assessing feature significance and confidence intervals with exact coverage for estimating population-level feature importance. The approach requires minimal assumptions, avoids model retraining or auxiliary models, and remains computationally efficient even for large-scale, high-dimensional settings. Experiments on synthetic tasks validate its statistical and computational advantages, and applications to real-world data illustrate its practical utility.

In higher education, many institutions use algorithmic alerts to flag at-risk students and deliver advising at scale. While much research has focused on evaluating algorithmic predictions, relatively little is known about how discretionary interventions by human experts shape outcomes in algorithm-assisted settings. We study this question using rich quantitative and qualitative data from a randomized controlled trial of an algorithm-assisted advising program at Georgia State University. Taking a mixed-methods approach, we examine whether and how advisors use context unavailable to an algorithm to guide interventions and influence student success. We develop a causal graphical framework for human expertise in the interventional setting, extending prior work on discretion in purely predictive settings. We then test a necessary condition for discretionary expertise using structured advisor logs and student outcomes data, identifying several interventions that meet the criterion for statistical significance. Accordingly, we estimate that 2 out of 3 interventions taken by advisors in the treatment arm were plausibly "expertly targeted" to students using non-algorithmic context. Systematic qualitative analysis of advisor notes corroborates these findings, showing a pattern of advisors incorporating diverse forms of contextual information--such as personal circumstances, financial issues, and student engagement--into their decisions. Our results offer theoretical and practical insight into the real-world effectiveness of algorithm-supported college advising, and underscore the importance of accounting for human expertise in the design, evaluation, and implementation of algorithmic decision systems.