Journal of Cyber Security, Privacy Issues and Challenges

Rubik-Inspired GraphRAG Loops: Autonomous AI Planning and Quantum Gate Optimization

Prashant D. Sawant — 2026-10-14

Autonomous artificial intelligence agents deployed in nondeterministic operational environments routinely encounter NP-hard planning challenges in which state permutation spaces grow exponentially with problem scale. Autoregressive large language model (LLM) reasoning chains degrade under such conditions, exhibiting compounding token drift, context-window saturation, and elevated rates of invalid state transitions. This paper introduces the Group-Theoretic GraphRAG Loop (GT-GRL) framework, a mathematically grounded architecture that unifies group-theoretic Cayley graph representations, structural Retrieval-Augmented Generation (GraphRAG), and cyclic multi-agent state machines implemented with LangGraph. The central analogy drawn from Rubik’s Cube combinatorics is that a permutation space of configurations is navigable in at most twenty deterministic moves by exploiting the algebraic structure of the underlying group. GT-GRL models decision domains as algebraic permutation groups and projects high-dimensional problem topologies onto structured Cayley graphs. A cyclic, self-correcting agent loop executes subgroup decomposition and coset navigation, collapsing state spaces exceeding permutations into deterministic trajectories of ten or fewer operational steps when the stabiliser subgroup chain is precomputed from a stable generator set; dynamic recomputation when generators change introduces additional polynomial-time overhead. Framework evaluation is presented via simulated proof-of-concept models across two test domains: an enterprise zero-trust cybersecurity network and a quantum circuit gate compilation benchmark on noisy intermediate-scale quantum (NISQ) hardware. In a controlled synthetic cybersecurity simulation, GT-GRL demonstrated theoretical threat containment in 185 ms (simulation-internal clock time, excluding network and API propagation overhead) with a simulated false-positive rate of 0.02%. In simulated quantum compilation models, the framework achieved up to a 42% reduction in circuit depth relative to standard heuristic compilers on the tested benchmark suite. In conclusion, this paper further outlines theoretical and conceptual frameworks for extending algebraic planning to four additional candidate domains: multi-hop financial fraud interdiction, retrosynthetic pharmaceutical pathway optimisation, post-quantum cryptography migration, and industrial robotics trajectory planning.

Machine Learning-Based Phishing Website Identification System

Mubeena Banu — 2026-09-09

The rapid growth of online services has led to a significant increase in phishing attacks, making phishing website detection a critical area of cybersecurity research. Machine learning techniques have emerged as an effective solution by enabling faster and more accurate identification of fraudulent websites. This literature survey reviews four recent studies that apply different machine learning approaches, including Random Forest, Support Vector Machine (SVM), Decision Tree, hybrid models, and AI-driven techniques, for phishing website detection. The reviewed works examine various URL-based, domain-related, and webpage content features to distinguish malicious websites from legitimate ones while addressing issues such as changing phishing strategies, feature selection, and real-time detection. A comparative analysis of these studies highlights their methodologies, performance, advantages, and limitations, helping to identify current research trends and existing challenges. Based on the findings, the survey indicates that integrating effective feature engineering with the Random Forest algorithm can improve the accuracy and reliability of real-time phishing detection systems. The study also provides useful insights for designing practical, secure, and user-friendly solutions that strengthen cybersecurity and promote safer web browsing.

Enhancing Cybersecurity with Machine Learning: Threat Detection, Challenges, Emerging Trends, and Future Directions

Chandra Sekhar Koppireddy — 2026-09-30

Cybersecurity threats are becoming increasingly sophisticated and persistent due to the rapid adoption of digital technologies, cloud computing, and interconnected network infrastructures. Organizations and institutions increasingly rely on these technologies to store sensitive information, conduct financial transactions, support critical operations, and facilitate secure communication. However, the continuous evolution of technology has also enabled cybercriminals to develop sophisticated techniques for bypassing security mechanisms across software, hardware, and network environments. Traditional security measures, including firewalls and antivirus solutions, are often insufficient to effectively address emerging and advanced cyber threats. To deal with these problems, organizations need security systems that can adapt and learn and can find unknown threats. Machine learning is a way to do this because it can look at a lot of data, find patterns that are not easy to see and find things that are not normal in network traffic. Machine learning also gets better at finding threats over time. It helps organizations respond to cyberattacks faster. This research is about making cybersecurity better using machine learning, the challenges that come with it and how it can be used in the future to keep security systems safe around the world. Cybersecurity is a big deal, and machine learning can help with cybersecurity. Cybersecurity threats are a problem, and machine learning can help with cybersecurity.