The paper proposes Triumvir, a multi-modal ensemble architecture that significantly improves the classification of small, raw data fragments to distinguish between encrypted and compressed data, outpe…

This paper proposes a hybrid feature fusion and voting-based approach for automated malware detection and classification into specific malware families, achieving high performance metrics like an AUC…

The paper introduces a novel byte-level method to encode network flow records into fixed-size RGB images, significantly improving the performance of Intrusion Detection Systems (IDS) by allowing convo…

This paper proposes a hybrid CNN-LSTM framework to enhance cyber attack detection and prevention in U.S. critical digital infrastructure by evaluating multiple machine learning models on the CSE-CIC-I…

This paper proposes and evaluates the KAN-LSTM model, demonstrating that Kolmogorov-Arnold Networks (KANs) significantly outperform traditional deep learning models for accurate and parameter-efficien…

The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…

The paper introduces i-SDT, an intelligent Self-Defending Digital Twin, which enhances cyber-physical security by accurately discriminating various attack types and maintaining safe operation without…

This paper reviews current trends in AI-based cybersecurity, specifically analyzing various AI techniques applied to intrusion detection to provide comparative insights.

The paper empirically evaluates domain-adapted and general-purpose LLMs for structured threat modelling (STRIDE on 5G security), finding that domain adaptation and model size do not guarantee reliable…

The paper proposes an enhanced Wasserstein GAN with Gradient Penalty (SA-JS-WGAN-GP) incorporating Self-Attention and Jensen-Shannon Divergence to synthesize diverse network traffic data, significantl…

The paper introduces EnsembleSHAP, a novel, computationally efficient, and provably robust feature attribution method specifically designed for the Random Subspace Method to provide secure explanation…

The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…

The paper proposes a multi-modal contrastive learning framework to improve the generalization of machine learning models in cybersecurity by transferring knowledge from rich textual vulnerability desc…

This paper proposes an explainable threat attribution system for IoT networks that uses SHAP and flow behavior modeling to accurately classify and explain over 30 distinct attack variants into 8 meani…

SentinelSphere is an AI platform that integrates advanced deep learning for real-time threat detection with an LLM-powered training system to holistically address both technical and human-factor cyber…

By analyzing over 27,000 posts from 325 public ransomware leak sites, this paper demonstrates that ransomware groups exhibit non-random, predictable operational regularities concerning victim concentr…

This paper analyzes the latency-accuracy trade-offs of various TinyML models for detecting diverse cyber-RF threats on autonomous spacecraft, finding that Logistic Regression offers an effective, low-…

MambaNetBurst introduces a compact, tokenizer-free byte-level classifier using a Mamba-2 backbone to achieve strong network traffic classification without requiring pre-training or complex data prepro…

This paper provides the first systematic threat analysis of State-Space Models (SSMs) in safety-critical applications, introducing novel attack classes and formal metrics to quantify their security an…