Archives - Page 4

• 

  Cryptography beyond Quantum threats

  Vol. 2 No. 09 (2025)

  Abstract

  Quantum computers threaten many widely used public-key cryptosystems (RSA, ECC) by enabling Shor-style algorithms that efficiently solve integer factorization and discrete logarithms. Post-Quantum Cryptography (PQC) replaces vulnerable number-theory primitives with schemes based on problems believed hard for both classical and quantum adversaries (lattices, codes, hash-based, multivariate systems). This paper surveys the current PQC landscape, highlights the leading algorithms recommended for standardization, evaluates their performance and security trade-offs, and presents a practical methodology for adopting PQC (hybridization, crypto-agility, benchmarking and TLS integration). We report recent implementation and benchmark findings showing lattice-based schemes (e.g., CRYSTALS-Kyber for key-encapsulation, CRYSTALS-Dilithium/FALCON for signatures) provide strong security with practical performance for many real-world scenarios, while some alternative families (isogeny-based SIKE) were broken and illustrate the need for conservative migration strategies. Finally, we give deployment recommendations (hybrid KEMs in TLS, phased rollout, crypto-inventory) and an agenda for future research (parameter selection, side-channel resistance, efficient signatures).

  Index Terms

  Post-Quantum Cryptography (PQC), Quantum-Resistant Cryptography, Lattice-Based Cryptography, Learning with Errors (LWE), CRYSTALS-Kyber (Key Encapsulation Mechanism), CRYSTALS-Dilithium (Digital Signatures), FALCON Signatures, SPHINCS+ (Hash-Based Signatures), Code-Based Cryptography (McEliece), Multivariate Polynomial Cryptography, Isogeny-Based Cryptography (SIKE, CSIDH), Hybrid Key Exchange Protocols, TLS 1.3 and PQC Integration, Crypto-Agility, Side-Channel Attack Resistance, Secure Public Key Infrastructure (PKI), Long-Term Confidentiality, Harvest-Now-Decrypt-Later Attacks, Quantum Threat Models, Standardization (NIST PQC Project).

• 

  AI-Driven Hybrid System for Personalized Movie Recommendations

  Vol. 2 No. 02 (2025)

  Abstract:

  This paper introduces a novel hybrid recommendation system that integrates content-based and collaborative filtering approaches using deep learning techniques to enhance movie recommendations. Our model merges the metadata of movies, including genres, cast, and crew from the MovieLens dataset with user ratings to construct a comprehensive feature set. We employ a Term Frequency-Inverse Document Frequency (TF-IDF) vectorizer to extract content-based features and utilize Singular Value Decomposition (SVD) to derive collaborative filtering features, thereby addressing both user preferences and item characteristics.We further enhance the model by concatenating these features into a unified representation, which is then processed through a deep neural network to predict movie ratings. The network architecture consists of multiple dense layers with dropout regularization to prevent overfitting, ensuring robustness in learning complex user-item interactions. We evaluate our model on a standard dataset, focusing on mean squared error (MSE) as the performance metric to assess accuracy.The results demonstrate the effectiveness of our hybrid approach in providing precise recommendations by leveraging both the semantic content of movies and the historical interactions of users, thereby outperforming traditional methods that rely on singular recommendation strategies. This research contributes to the recommendation system community by showcasing a scalable and efficient method to improve recommendation quality and user satisfaction in multimedia services.

  Keywords- Recommendation systems, Deep learning, Hybrid models, Collaborative filtering, Content-based filtering, MovieLens dataset, TF-IDF vectorization, Singular Value Decomposition, Neural networks, User-item interaction, Multimedia services, Movie recommendations, Personalization, Machine learning, Artificial intelligence.