arXiv subjects

Kelly Cohen

Publications and source records attributed to Kelly Cohen.

At least 19 recordsLinked to original sources

arXiv2026

Optimal Take-off under Fuzzy Clearances

This paper presents a hybrid obstacle avoidance architecture that integrates Optimal Control under clearance with a Fuzzy Rule Based System (FRBS) to enable adaptive constraint handling for unmanned aircraft. Motivated by the limitations of classical optimal control under uncertainty and the need for interpretable decision making in safety critical aviation systems, we design a three stage Takagi Sugeno Kang fuzzy layer that modulates constraint radii, urgency levels, and activation decisions based on regulatory separation minima and airworthiness guidelines from FAA and EASA. These fuzzy-derived clearances are then incorporated as soft constraints into an optimal control problem solved using the FALCON toolbox and IPOPT. The framework aims to reduce unnecessary recomputations by selectively activating obstacle avoidance updates while maintaining compliance with aviation procedures. A proof of concept implementation using a simplified aircraft model demonstrates that the approach can generate optimal trajectories with computation times of 2,3 seconds per iteration in a single threaded MATLAB environment, suggesting feasibility for near real time applications. However, our experiments revealed a critical software incompatibility in the latest versions of FALCON and IPOPT, in which the Lagrangian penalty term remained identically zero, preventing proper constraint enforcement. This behavior was consistent across scenarios and indicates a solver toolbox regression rather than a modeling flaw. Future work includes validating this effect by reverting to earlier software versions, optimizing the fuzzy membership functions using evolutionary methods, and extending the system to higher fidelity aircraft models and stochastic obstacle environments.

cs.AI↗

arXiv2026

Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction

Detecting jailbreak attempts in clinical training large language models (LLMs) requires accurate modeling of linguistic deviations that signal unsafe or off-task user behavior. Prior work on the 2-Sigma clinical simulation platform showed that manually annotated linguistic features could support jailbreak detection. However, reliance on manual annotation limited both scalability and expressiveness. In this study, we extend this framework by using experts' annotations of four core linguistic features (Professionalism, Medical Relevance, Ethical Behavior, and Contextual Distraction) and training multiple general-domain and medical-domain BERT-based LLM models to predict these features directly from text. The most reliable feature regressor for each dimension was selected and used as the feature extractor in a second layer of classifiers. We evaluate a suite of predictive models, including tree-based, linear, probabilistic, and ensemble methods, to determine jailbreak likelihood from the extracted features. Across cross-validation and held-out evaluations, the system achieves strong overall performance, indicating that LLM-derived linguistic features provide an effective basis for automated jailbreak detection. Error analysis further highlights key limitations in current annotations and feature representations, pointing toward future improvements such as richer annotation schemes, finer-grained feature extraction, and methods that capture the evolving risk of jailbreak behavior over the course of a dialogue. This work demonstrates a scalable and interpretable approach for detecting jailbreak behavior in safety-critical clinical dialogue systems.

cs.AI↗

arXiv2026

Rule-Based Spatial Mixture-of-Experts U-Net for Explainable Edge Detection

Deep learning models like U-Net and its variants, have established state-of-the-art performance in edge detection tasks and are used by Generative AI services world-wide for their image generation models. However, their decision-making processes remain opaque, operating as "black boxes" that obscure the rationale behind specific boundary predictions. This lack of transparency is a critical barrier in safety-critical applications where verification is mandatory. To bridge the gap between high-performance deep learning and interpretable logic, we propose the Rule-Based Spatial Mixture-of-Experts U-Net (sMoE U-Net). Our architecture introduces two key innovations: (1) Spatially-Adaptive Mixture-of-Experts (sMoE) blocks integrated into the decoder skip connections, which dynamically gate between "Context" (smooth) and "Boundary" (sharp) experts based on local feature statistics; and (2) a Takagi-Sugeno-Kang (TSK) Fuzzy Head that replaces the standard classification layer. This fuzzy head fuses deep semantic features with heuristic edge signals using explicit IF-THEN rules. We evaluate our method on the BSDS500 benchmark, achieving an Optimal Dataset Scale (ODS) F-score of 0.7628, effectively matching purely deep baselines like HED (0.7688) while outperforming the standard U-Net (0.7437). Crucially, our model provides pixel-level explainability through "Rule Firing Maps" and "Strategy Maps," allowing users to visualize whether an edge was detected due to strong gradients, high semantic confidence, or specific logical rule combinations.

cs.CE↗

arXiv2026

A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures

Convolutional Neural Networks (CNNs) achieve strong image classification performance but lack interpretability and are vulnerable to adversarial attacks. Neuro-fuzzy hybrids such as DCNFIS replace fully connected CNN classifiers with Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to improve interpretability, yet their robustness remains underexplored. This work compares standard CNNs (ConvNet, VGG, ResNet18) with their ANFIS-augmented counterparts on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 under gradient-based (PGD) and gradient-free (Square) attacks. Results show that ANFIS integration does not consistently improve clean accuracy and has architecture-dependent effects on robustness: ResNet18-ANFIS exhibits improved adversarial robustness, while VGG-ANFIS often underperforms its baseline. These findings suggest that neuro-fuzzy augmentation can enhance robustness in specific architectures but is not universally beneficial.

cs.CV↗

arXiv2026

Genetic Generalized Additive Models

Generalized Additive Models (GAMs) balance predictive accuracy and interpretability, but manually configuring their structure is challenging. We propose using the multi-objective genetic algorithm NSGA-II to automatically optimize GAMs, jointly minimizing prediction error (RMSE) and a Complexity Penalty that captures sparsity, smoothness, and uncertainty. Experiments on the California Housing dataset show that NSGA-II discovers GAMs that outperform baseline LinearGAMs in accuracy or match performance with substantially lower complexity. The resulting models are simpler, smoother, and exhibit narrower confidence intervals, enhancing interpretability. This framework provides a general approach for automated optimization of transparent, high-performing models. The code can be found at https://github.com/KaaustaaubShankar/GeneticAdditiveModels.

cs.LG↗

arXiv2025

Fuzzy Decisions on Fluid Instabilities: Autoencoder-Based Reconstruction meets Rule-Based Anomaly Classification

Shockwave classification in shadowgraph imaging is challenging due to limited labeled data and complex flow structures. This study presents a hybrid framework that combines unsupervised autoencoder models with a fuzzy inference system to generate and interpret anomaly maps. Among the evaluated methods, the hybrid $\beta$-VAE autoencoder with a fuzzy rule-based system most effectively captured coherent shock features, integrating spatial context to enhance anomaly classification. The resulting approach enables interpretable, unsupervised classification of flow disruptions and lays the groundwork for real-time, physics-informed diagnostics in experimental and industrial fluid applications.

cs.CE↗

arXiv2025

On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization

We present a reinforcement learning method for training neuro-fuzzy controllers using Proximal Policy Optimization (PPO). Unlike prior approaches that used Deep Q-Networks (DQN) with Adaptive Neuro-Fuzzy Inference Systems (ANFIS), our PPO-based framework leverages a stable on-policy actor-critic setup. Evaluated on the CartPole-v1 environment across multiple seeds, PPO-trained fuzzy agents consistently achieved the maximum return of 500 with zero variance after 20000 updates, outperforming ANFIS-DQN baselines in both stability and convergence speed. This highlights PPO's potential for training explainable neuro-fuzzy agents in reinforcement learning tasks.

cs.LG↗

arXiv2025

Comparative of Genetic Fuzzy regression techniques for aeroacoustic phenomenons

This study investigates the application of Genetic Fuzzy Systems (GFS) to model the self-noise generated by airfoils, a key issue in aeroaccoustics with significant implications for aerospace, automotive and drone applications. Using the publicly available Airfoil Self Noise dataset, various Fuzzy regression strategies are explored and compared. The paper evaluates a brute force Takagi Sugeno Kang (TSK) fuzzy system with high rule density, a cascading Geneti Fuzzy Tree (GFT) architecture and a novel clustered approach based on Fuzzy C-means (FCM) to reduce the model's complexity. This highlights the viability of clustering assisted fuzzy inference as an effective regression tool for complex aero accoustic phenomena. Keywords : Fuzzy logic, Regression, Cascading systems, Clustering and AI.

cs.AI↗

arXiv2025

Reducing Student Distraction Through Fuzzy Logic Based Seating Arrangements

A crucial skill for primary school teachers is maintaining efficient classroom management. Teachers use classroom seating arrangements to help maintain this efficiency. However, developing classroom seating arrangements is both time-consuming and often non-optimal for distraction mitigation. Fuzzy logic-based approaches for the development of classroom seating arrangements can reduce development time and minimize classroom distraction. In this study, an original fuzzy logic-based software package named "CUB" is introduced and applied to a modern classroom using "cluster" seating arrangements. The combination of fuzzy inference systems, fuzzy c-means clustering, sequential, and iterative processes produce ready-to-use seating arrangements for the classroom in this study. The seating arrangements are compared with an existing set of seating arrangements to validate the results. The author's findings show that CUB is successful in generating applicable seating arrangements with a small liklihood of replicating arrangements. The findings also suggest that fuzz logic-based approaches may be successful in other styles of classroom arrangement.

cs.LO↗

arXiv2025

A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection

Phishing attacks represent an increasingly sophisticated and pervasive threat to individuals and organizations, causing significant financial losses, identity theft, and severe damage to institutional reputations. Existing phishing detection methods often struggle to simultaneously achieve high accuracy and explainability, either failing to detect novel attacks or operating as opaque black-box models. To address this critical gap, we propose a novel phishing URL detection system based on a first-order Takagi-Sugeno-Kang (TSK) fuzzy inference model optimized through gradient-based techniques. Our approach intelligently combines the interpretability and human-like reasoning capabilities of fuzzy logic with the precision and adaptability provided by gradient optimization methods, specifically leveraging the Adam optimizer for efficient parameter tuning. Experiments conducted using a comprehensive dataset of over 235,000 URLs demonstrate rapid convergence, exceptional predictive performance (accuracy averaging 99.95% across 5 cross-validation folds, with a perfect AUC i.e. 1.00). Furthermore, optimized fuzzy rules and membership functions improve interoperability, clearly indicating how the model makes decisions - an essential feature for cybersecurity applications. This high-performance, transparent, and interpretable phishing detection framework significantly advances current cybersecurity defenses, providing practitioners with accurate and explainable decision-making tools.

cs.CR↗

arXiv2025

Fuzzy-RRT for Obstacle Avoidance in a 2-DOF Semi-Autonomous Surgical Robotic Arm

AI-driven semi-autonomous robotic surgery is essential for addressing the medical challenges of long-duration interplanetary missions, where limited crew sizes and communication delays restrict traditional surgical approaches. Current robotic surgery systems require full surgeon control, demanding extensive expertise and limiting feasibility in space. We propose a novel adaptation of the Fuzzy Rapidly-exploring Random Tree algorithm for obstacle avoidance and collaborative control in a two-degree-of-freedom robotic arm modeled on the Miniaturized Robotic-Assisted surgical system. It was found that the Fuzzy Rapidly-exploring Random Tree algorithm resulted in an 743 percent improvement to path search time and 43 percent improvement to path cost.

cs.RO↗

arXiv2025

Gradient-Optimized Fuzzy Classifier: A Benchmark Study Against State-of-the-Art Models

This paper presents a performance benchmarking study of a Gradient-Optimized Fuzzy Inference System (GF) classifier against several state-of-the-art machine learning models, including Random Forest, XGBoost, Logistic Regression, Support Vector Machines, and Neural Networks. The evaluation was conducted across five datasets from the UCI Machine Learning Repository, each chosen for their diversity in input types, class distributions, and classification complexity. Unlike traditional Fuzzy Inference Systems that rely on derivative-free optimization methods, the GF leverages gradient descent to significantly improving training efficiency and predictive performance. Results demonstrate that the GF model achieved competitive, and in several cases superior, classification accuracy while maintaining high precision and exceptionally low training times. In particular, the GF exhibited strong consistency across folds and datasets, underscoring its robustness in handling noisy data and variable feature sets. These findings support the potential of gradient optimized fuzzy systems as interpretable, efficient, and adaptable alternatives to more complex deep learning models in supervised learning tasks.

cs.LG↗

arXiv2025

A Genetic Fuzzy-Enabled Framework on Robotic Manipulation for In-Space Servicing

Automation of robotic systems for servicing in cislunar space is becoming extremely important as the number of satellites in orbit increases. Safety is critical in performing satellite maintenance, so the control techniques utilized must be trusted in addition to being highly efficient. In this work, Genetic Fuzzy Trees are combined with the widely used LQR control scheme via Thales' TrUE AI Toolkit to create a trusted and efficient controller for a two-degree-of-freedom planar robotic manipulator that would theoretically be used to perform satellite maintenance. It was found that Genetic Fuzzy-LQR is 18.5% more performant than optimal LQR on average, and that it is incredibly robust to uncertainty.

cs.RO↗

arXiv2025

Fuzzy Logic -- Based Scheduling System for Part-Time Workforce

This paper explores the application of genetic fuzzy systems to efficiently generate schedules for a team of part-time student workers at a university. Given the preferred number of working hours and availability of employees, our model generates feasible solutions considering various factors, such as maximum weekly hours, required number of workers on duty, and the preferred number of working hours. The algorithm is trained and tested with availability data collected from students at the University of Cincinnati. The results demonstrate the algorithm's efficiency in producing schedules that meet operational criteria and its robustness in understaffed conditions.

cs.NE↗

arXiv2025

Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models

Jailbreaking in Large Language Models (LLMs) threatens their safe use in sensitive domains like education by allowing users to bypass ethical safeguards. This study focuses on detecting jailbreaks in 2-Sigma, a clinical education platform that simulates patient interactions using LLMs. We annotated over 2,300 prompts across 158 conversations using four linguistic variables shown to correlate strongly with jailbreak behavior. The extracted features were used to train several predictive models, including Decision Trees, Fuzzy Logic-based classifiers, Boosting methods, and Logistic Regression. Results show that feature-based predictive models consistently outperformed Prompt Engineering, with the Fuzzy Decision Tree achieving the best overall performance. Our findings demonstrate that linguistic-feature-based models are effective and explainable alternatives for jailbreak detection. We suggest future work explore hybrid frameworks that integrate prompt-based flexibility with rule-based robustness for real-time, spectrum-based jailbreak monitoring in educational LLMs.

cs.CL↗

arXiv2025

A model agnostic eXplainable AI based fuzzy framework for sensor constrained Aerospace maintenance applications

Machine Learning methods have extensively evolved to support industrial big data methods and their corresponding need in gas turbine maintenance and prognostics. However, most unsupervised methods need extensively labeled data to perform predictions across many dimensions. The cutting edge of small and medium applications do not necessarily maintain operational sensors and data acquisition with rising costs and diminishing profits. We propose a framework to make sensor maintenance priority decisions using a combination of SHAP, UMAP, Fuzzy C-means clustering. An aerospace jet engine dataset is used as a case study.

cs.CE↗

arXiv2024

Zero Trust Implementation in the Emerging Technologies Era: Survey

This paper presents a comprehensive analysis of the shift from the traditional perimeter model of security to the Zero Trust (ZT) framework, emphasizing the key points in the transition and the practical application of ZT. It outlines the differences between ZT policies and legacy security policies, along with the significant events that have impacted the evolution of ZT. Additionally, the paper explores the potential impacts of emerging technologies, such as Artificial Intelligence (AI) and quantum computing, on the policy and implementation of ZT. The study thoroughly examines how AI can enhance ZT by utilizing Machine Learning (ML) algorithms to analyze patterns, detect anomalies, and predict threats, thereby improving real-time decision-making processes. Furthermore, the paper demonstrates how a chaos theory-based approach, in conjunction with other technologies like eXtended Detection and Response (XDR), can effectively mitigate cyberattacks. As quantum computing presents new challenges to ZT and cybersecurity as a whole, the paper delves into the intricacies of ZT migration, automation, and orchestration, addressing the complexities associated with these aspects. Finally, the paper provides a best practice approach for the seamless implementation of ZT in organizations, laying out the proposed guidelines to facilitate organizations in their transition towards a more secure ZT model. The study aims to support organizations in successfully implementing ZT and enhancing their cybersecurity measures.

cs.CR↗

arXiv2023

Explainable AI Insights for Symbolic Computation: A case study on selecting the variable ordering for cylindrical algebraic decomposition

In recent years there has been increased use of machine learning (ML) techniques within mathematics, including symbolic computation where it may be applied safely to optimise or select algorithms. This paper explores whether using explainable AI (XAI) techniques on such ML models can offer new insight for symbolic computation, inspiring new implementations within computer algebra systems that do not directly call upon AI tools. We present a case study on the use of ML to select the variable ordering for cylindrical algebraic decomposition. It has already been demonstrated that ML can make the choice well, but here we show how the SHAP tool for explainability can be used to inform new heuristics of a size and complexity similar to those human-designed heuristics currently commonly used in symbolic computation.

cs.SC↗