Research Article
Special Coverings of Sets and Boolean Functions
Issue:
Volume 10, Issue 3, September 2025
Pages:
84-97
Received:
13 June 2025
Accepted:
30 June 2025
Published:
23 July 2025
Abstract: We will study some properties of Boolean functions based on newly introduced concepts called “Special Decomposition of a Set’’ and “Special Covering of a Set’’. The introduced concepts easily solve the question of how changes in clauses affect the resulting value of a function. They easily determine a clause as well as the literals that can be added to or removed from the clause so that the satisfiability of the function is preserved. The concept of generating a satisfiable function by another satisfiable function through admissible changes in the function's clauses is also introduced. If the generation of a function by another function is defined as a binary relation, then the set of satisfiable functions of n variables, represented in conjunctive normal form with m clauses is partitioned to equivalence classes. Moreover, we prove that any two satisfiable Boolean functions of n variables, represented in conjunctive normal form with m clauses, can be generated from each other in polynomial time.
Abstract: We will study some properties of Boolean functions based on newly introduced concepts called “Special Decomposition of a Set’’ and “Special Covering of a Set’’. The introduced concepts easily solve the question of how changes in clauses affect the resulting value of a function. They easily determine a clause as well as the literals that can be adde...
Show More
Research Article
Hybrid CNN-LSTM Architectures for Deepfake Audio Detection Using Mel Frequency Cepstral Coefficients and Spectogram Analysis
Issue:
Volume 10, Issue 3, September 2025
Pages:
98-109
Received:
23 August 2025
Accepted:
4 September 2025
Published:
25 September 2025
DOI:
10.11648/j.ajmcm.20251003.12
Downloads:
Views:
Abstract: The rapid advancement of AI-generated synthetic speech poses significant threats, including identity fraud and misinformation, as deepfake audio becomes increasingly indistinguishable from genuine recordings. While existing detection methods have achieved high accuracy on specific datasets, they often struggle with generalization across diverse audio samples and real-world conditions. To address this limitation, this paper proposes a hybrid Deep CNN-LSTM model that leverages both Mel Frequency Cepstral Coefficients (MFCCs) and spectrogram analysis to capture complementary spatial and temporal artifacts indicative of synthetic speech. The model was evaluated on the Fake-or-Real (FoR) dataset, achieving a classification accuracy of 94.7%, surpassing standalone CNN (87.3%) and LSTM (82.7%) models. Crucially, the model demonstrated strong generalization capabilities with an AUC-ROC score of 97.3%. Further cross-dataset evaluation on ASVspoof 2019 confirmed its robustness, achieving an accuracy of 93.2%. The results indicate that the fusion of spectral and temporal features through a hybrid architecture provides a more robust solution for detecting AI-generated audio, contributing to the development of reliable deepfake detection systems for cybersecurity and digital forensics applications.
Abstract: The rapid advancement of AI-generated synthetic speech poses significant threats, including identity fraud and misinformation, as deepfake audio becomes increasingly indistinguishable from genuine recordings. While existing detection methods have achieved high accuracy on specific datasets, they often struggle with generalization across diverse aud...
Show More