💻 Category

cs

3031 papers

💻 computer science

Training Versus Hiring in Security Operations Centers: Agent-Based and Reinforcement Learning Simulations of Training Duration Effects on CyberTeam Performance

This study utilizes agent-based modeling and reinforcement learning to demonstrate that training duration in Security Operations Centers yields nonlinear performance gains, with optimal investment occurring between 500 and 1,000 episodes and highly trained teams achieving efficiency advantages equivalent to recruiting 20–25 additional personnel.

Max N. Yaw, Ferdinand Kpieleh, Aos Mulahuwaish, Basheer Qolomany, Jacques Bou Abdo2026-06-27
💻 computer science

Quantifying the Security-Performance Trade-off in Constrained IoT: A Multi-Vector MQTT Attack Framework with Hybrid Defense-in-Depth Evaluation

This paper presents a reproducible experimental framework demonstrating that chaining physical HID intrusions with MQTT network attacks exposes critical security-performance trade-offs in constrained IoT devices, revealing that while TLS offers strong confidentiality, it incurs prohibitive latency and memory costs on legacy hardware, thereby motivating a novel Hybrid Defense-in-Depth architecture that prioritizes Access Control Lists for efficient, scalable protection.

Thant Zin Moe, Julia Juremi, Manimegalai Rajenderan2026-06-27
💻 computer science

Enhancing Cognitive Diagnosis with Group-Aware Graph Augmentation and Self-Supervised Alignment

This paper proposes the Group-Aware Cognitive Diagnosis (GACD) framework, which addresses data sparsity in student response data by grouping students with similar patterns, decomposing interactions into correct and incorrect subgraphs for independent learning, and employing self-supervised alignment to enhance the accuracy of cognitive state assessment.

Xiaomeng Zhang, Ruxiang Liu, Piao Shi, Qun Ren2026-06-26
💻 computer science

HERO-SNN: A Homeostatic Eligibility-based Reward- Optimised Spiking Neural Network for Spatiotemporal Brain Representation: An EEG Case Study

This paper proposes HERO-SNN, a homeostatic and reward-optimized spiking neural network framework that integrates task-specific feedback with local spike-based learning to enhance the classification accuracy and interpretability of spatiotemporal EEG data, outperforming both standard STDP and state-of-the-art deep learning models in a Havening-based touch protocol study.

Maryam Doborjeh, Zohreh Doborjeh, Nikola Kasabov, Alexander Sumich, Nadja Heym, Tony Burgess2026-06-26
💻 computer science

FDCNet: Frequency-Aware and Dynamic Curve Network for Adversarially Robust Infrared and Visible Image Fusion

This paper proposes FDCNet, a novel adversarially robust infrared and visible image fusion framework that integrates a Frequency-Aware Defense Module and a Spatio-Frequency Dynamic Adversarial Loss to suppress perturbations, while employing an Extrema-guided Dynamic Tone Curve Module to balance defense effectiveness with visual quality restoration.

Pengcheng Gao, Shengyue Huang2026-06-26
💻 computer science

DeepNeutroBiLSTM: A Hybrid Neutrosophic and CNN-BiLSTM Framework with Sobel-Based Indeterminacy for Arabic Handwritten Character Recognition

This paper proposes DeepNeutroBiLSTM, a novel hybrid framework integrating neutrosophic uncertainty modeling with Sobel-based indeterminacy, CNNs, and BiLSTMs to achieve state-of-the-art accuracy and robustness in Arabic handwritten character recognition on the AHCD and HIJJA datasets.

Othmane Farhaoui, Mohamed Rida Fethi, Imad Zeroual, Ahmad El Allaoui2026-06-26