Massimo Orazio Spata
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Massimo Orazio Spata has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Sebastiano Battiato
University of Catania, Catania, Italy
13 shared publications - Alessandro Ortis
University of Catania
7 shared publications - Francesco Rundo
University of Catania
5 shared publications Salvatore Rinaudo
STMicroelectronics, IPG - R&D, Catania, Italy
4 shared publications- Angelo Alberto Messina
STMicroelectronics, 95121 Catania, Italy
2 shared publications - Carmelo Pino
STMicroelectronics ADG, R &D Power and Discretes
2 shared publications
Latest Publications
- Open Access
- 6 September 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (9) , 561
Biovid dataset and challenge: biometric user recognition on smartphone data in real-world conditions
User authentication is more and more crucial in everyday life, with researchers developing sophisticated, yet easy-to-use, approaches to enforce secure authentication while providing a smooth user experience. This is particularly true in mobile authentication, in which the spread of AI-capable smartphones is opening up several biometric-based authentication methods, such as face and lips recognition. A more recently emerging setup consists of the matching of a spoken passphrase with lips movements. Despite being promising and well-suited for mobility authentication, the matching operation is not trivial, and the research around this topic is limited, as no publicly available dataset is available for experimental purposes. In this paper we thus introduce BioVid , a novel privacy-aware multimodal biometric dataset for user recognition from smartphone-recorded videos in real-world conditions. BioVid consists of 650 recordings from 43 participants, where each clip captures a user pronouncing predefined passphrases while simultaneously acquiring audio and lips movements. The dataset is designed to support dual-factor biometric authentication, combining speaker-unique identity (UID) and passphrase verification, and explicitly models realistic variability in device type, recording distance, background, and ambient noise. Together with the data, we provide a detailed statistical analysis of the linguistic, visual, and acoustic properties of the data, highlighting its diversity and suitability for robust biometric system evaluation. Moreover, to test the quality of the collected dataset, we organised an international challenge on multimodal user authentication leveraging BioVid . In this paper we thus also describe the challenge protocol, baseline systems, and evaluation metrics, while also summarising the best-performing submitted approaches as measured by Equal Error Rate (EER). BioVid and the accompanying challenge aim to establish a reproducible benchmark for multimodal biometric authentication on consumer-grade smartphones and to foster further research on privacy-aware, real-world biometric systems.
- 6 September 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (9) , 561
Open AccessBiovid dataset and challenge: biometric user recognition on smartphone data in real-world conditions
User authentication is more and more crucial in everyday life, with researchers developing sophisticated, yet easy-to-use, approaches to enforce secure authentication while providing a smooth user experience. This is particularly true in mobile authentication, in which the spread of AI-capable smartphones is opening up several biometric-based authentication methods, such as face and lips recognition. A more recently emerging setup consists of the matching of a spoken passphrase with lips movements. Despite being promising and well-suited for mobility authentication, the matching operation is not trivial, and the research around this topic is limited, as no publicly available dataset is available for experimental purposes. In this paper we thus introduce BioVid , a novel privacy-aware multimodal biometric dataset for user recognition from smartphone-recorded videos in real-world conditions. BioVid consists of 650 recordings from 43 participants, where each clip captures a user pronouncing predefined passphrases while simultaneously acquiring audio and lips movements. The dataset is designed to support dual-factor biometric authentication, combining speaker-unique identity (UID) and passphrase verification, and explicitly models realistic variability in device type, recording distance, background, and ambient noise. Together with the data, we provide a detailed statistical analysis of the linguistic, visual, and acoustic properties of the data, highlighting its diversity and suitability for robust biometric system evaluation. Moreover, to test the quality of the collected dataset, we organised an international challenge on multimodal user authentication leveraging BioVid . In this paper we thus also describe the challenge protocol, baseline systems, and evaluation metrics, while also summarising the best-performing submitted approaches as measured by Equal Error Rate (EER). BioVid and the accompanying challenge aim to establish a reproducible benchmark for multimodal biometric authentication on consumer-grade smartphones and to foster further research on privacy-aware, real-world biometric systems.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 7, 1512-1523
Protocol-Aware, On-Device Per-Image ASD Classification on Saliency4ASD via Multi-Stream Distillation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 7, 1512-1523
Open AccessProtocol-Aware, On-Device Per-Image ASD Classification on Saliency4ASD via Multi-Stream Distillation
- Open Access
- 27 November 2025
- Published by Springer Nature in EURASIP Journal on Information Security
- Vol. 2025 (1) , 34
CNNMC: a convolutional neural network with Monte Carlo dropout for speaker recognition
- 27 November 2025
- Published by Springer Nature in EURASIP Journal on Information Security
- Vol. 2025 (1) , 34
Open AccessCNNMC: a convolutional neural network with Monte Carlo dropout for speaker recognition
- Open Access
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 182977-183001
Attractor-Aware Hyperbolic Lipschitz-Constrained-Reinforcement Learning for FX Market: LLM-Structured Chain of Thought With Lyapunov–Entropy Dynamics
Foreign exchange (FX) markets are non-stationary and event-driven, with heavy tails and regime shifts that complicate generalization and risk control.We introduce an explainable FX trading pipeline that integrates chaotic-systems diagnostics with geometry-aware learning. A Large Language Model (LLM) consolidates several dynamic heterogeneous evidence streams into a Structured Chain-of-Thought (s-CoT) that provides rules, supporting evidence, and uncertainties. The s-CoT is embedded in a hyperbolic space to preserve hierarchical dependencies and to render recurrent price levels geometrically salient. Chaotic and dynamical features, including Lyapunov exponents and permutation entropy, estimate local stability, forecastability horizons, and disorder. Recurrent magnet prices are identified as attractors on the price axis through recurrence density and cross-scale persistence, and they inform entry timing and risk budgeting. A Reinforcement Learning (RL) policy operates on the hyperbolic embedding under Lipschitz constraints that bound geodesic step sizes and stabilize policy updates under distribution shift. The result is an interpretable reasoning-to-action pipeline that produces daily decisions and explicit risk budgets. In pair-averaged non-compounding back-tests across nine major FX pairs from Jan. 2015 to July 2025, the system attains 2.22% monthly return with 10.39% maximum drawdown. An ablation study across components confirms the robustness of the full pipeline, indicating that geometry, Lipschitz control, and s-CoT jointly sustain performance while maintaining controlled drawdown. The empirical evaluation confirmed that encoding structured reasoning in hyperbolic space and steering actions toward magnet-price attractors yields regime-resilient FX trading with strong average performance and transparent risk control.
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 182977-183001
Open AccessAttractor-Aware Hyperbolic Lipschitz-Constrained-Reinforcement Learning for FX Market: LLM-Structured Chain of Thought With Lyapunov–Entropy Dynamics
Foreign exchange (FX) markets are non-stationary and event-driven, with heavy tails and regime shifts that complicate generalization and risk control.We introduce an explainable FX trading pipeline that integrates chaotic-systems diagnostics with geometry-aware learning. A Large Language Model (LLM) consolidates several dynamic heterogeneous evidence streams into a Structured Chain-of-Thought (s-CoT) that provides rules, supporting evidence, and uncertainties. The s-CoT is embedded in a hyperbolic space to preserve hierarchical dependencies and to render recurrent price levels geometrically salient. Chaotic and dynamical features, including Lyapunov exponents and permutation entropy, estimate local stability, forecastability horizons, and disorder. Recurrent magnet prices are identified as attractors on the price axis through recurrence density and cross-scale persistence, and they inform entry timing and risk budgeting. A Reinforcement Learning (RL) policy operates on the hyperbolic embedding under Lipschitz constraints that bound geodesic step sizes and stabilize policy updates under distribution shift. The result is an interpretable reasoning-to-action pipeline that produces daily decisions and explicit risk budgets. In pair-averaged non-compounding back-tests across nine major FX pairs from Jan. 2015 to July 2025, the system attains 2.22% monthly return with 10.39% maximum drawdown. An ablation study across components confirms the robustness of the full pipeline, indicating that geometry, Lipschitz control, and s-CoT jointly sustain performance while maintaining controlled drawdown. The empirical evaluation confirmed that encoding structured reasoning in hyperbolic space and steering actions toward magnet-price attractors yields regime-resilient FX trading with strong average performance and transparent risk control.
- Open Access
- 1 September 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (17) , 8482
Formation of 3D Human Osteoblast Spheroids Incorporating Extracellular Matrix-Mimetic Phage Peptides as a Surrogate Bone Tissue Model
Cell–cell communication and extracellular matrix (ECM) organization in a bone microenvironment are essential to replicate the bone microenvironment accurately. In this study, the extracellular matrix (ECM) was emulated by incorporating M13 phages, selected through phage display for displaying engineered peptides that mimic bone matrix proteins, into human osteoblast cultures to develop a three-dimensional bone model (3D BMP-Phage). Comprehensive analysis was performed to investigate: (i) the morphological development of spheroids, assessed by optical microscopy and quantified via fractal dimension analysis using box-counting algorithms; (ii) the biochemical composition of the extracellular matrix, evaluated by Raman spectroscopy; (iii) ECM protein deposition, analyzed through immunofluorescence staining; (iv) matrix mineralization, assessed by Alizarin Red staining and alkaline phosphatase (ALP) activity assay; and (v) osteogenic gene expression, measured by quantitative RT-PCR. The findings demonstrate that the 3D BMP-Phage model, facilitated by a cocktail of bone-mimicking peptides, enhances structural integrity, ECM complexity, mineralization, and osteogenic pathways compared to the control. This novel approach replicates key aspects of the bone microenvironment, providing a valuable platform for advanced physiological and regenerative medicine research under controlled conditions.
- 1 September 2025
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 26 (17) , 8482
Open AccessFormation of 3D Human Osteoblast Spheroids Incorporating Extracellular Matrix-Mimetic Phage Peptides as a Surrogate Bone Tissue Model
Cell–cell communication and extracellular matrix (ECM) organization in a bone microenvironment are essential to replicate the bone microenvironment accurately. In this study, the extracellular matrix (ECM) was emulated by incorporating M13 phages, selected through phage display for displaying engineered peptides that mimic bone matrix proteins, into human osteoblast cultures to develop a three-dimensional bone model (3D BMP-Phage). Comprehensive analysis was performed to investigate: (i) the morphological development of spheroids, assessed by optical microscopy and quantified via fractal dimension analysis using box-counting algorithms; (ii) the biochemical composition of the extracellular matrix, evaluated by Raman spectroscopy; (iii) ECM protein deposition, analyzed through immunofluorescence staining; (iv) matrix mineralization, assessed by Alizarin Red staining and alkaline phosphatase (ALP) activity assay; and (v) osteogenic gene expression, measured by quantitative RT-PCR. The findings demonstrate that the 3D BMP-Phage model, facilitated by a cocktail of bone-mimicking peptides, enhances structural integrity, ECM complexity, mineralization, and osteogenic pathways compared to the control. This novel approach replicates key aspects of the bone microenvironment, providing a valuable platform for advanced physiological and regenerative medicine research under controlled conditions.
- Open Access
- 26 May 2025
- Published by Springer Nature in Research Square
CNNMC: A Convolutional Neural Network with Monte Carlo Dropout for Speaker Recognition
Speaker recognition is the task of identifying or verifying a person’s identity using their voice. This problem involves challenges like variations in speech due to emotional states, health conditions, heterogeneity of microphones models, different environments and background noise. Accurate speaker recognition is critical for applications in security, personalized user experiences, and forensic analysis. Applying a CNN with Monte Carlo Dropout can enhance Speaker Recognition by leveraging unlabeled data to improve feature extraction and model robustness. This approach helps mitigate overfitting and enhances generalization, making it particularly effective in handling diverse and variable speech patterns in speaker recognition tasks. The designed deep learning model showcases superior performance in multiple dimensions achieving a peak validation accuracy of 92.07\% for speaker recognition on a specific dataset recorded in the wild by phone, and 0.038 of EER, obtaining good performance with respect the related prior art.
- 26 May 2025
- Published by Springer Nature in Research Square
Open AccessCNNMC: A Convolutional Neural Network with Monte Carlo Dropout for Speaker Recognition
Speaker recognition is the task of identifying or verifying a person’s identity using their voice. This problem involves challenges like variations in speech due to emotional states, health conditions, heterogeneity of microphones models, different environments and background noise. Accurate speaker recognition is critical for applications in security, personalized user experiences, and forensic analysis. Applying a CNN with Monte Carlo Dropout can enhance Speaker Recognition by leveraging unlabeled data to improve feature extraction and model robustness. This approach helps mitigate overfitting and enhances generalization, making it particularly effective in handling diverse and variable speech patterns in speaker recognition tasks. The designed deep learning model showcases superior performance in multiple dimensions achieving a peak validation accuracy of 92.07\% for speaker recognition on a specific dataset recorded in the wild by phone, and 0.038 of EER, obtaining good performance with respect the related prior art.
- Open Access
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 24498-24514
A New Pipeline for Snooping Keystroke Based on Deep Learning Algorithm
This research focuses on the vulnerability issues related to keystroke logging on a physical computer keyboard, known as Snooping Keystrokes. This category of attacks occurs recording an audio track with a smartphone while typing on the keyboard, and processing the audio to detect individual pressed keys. To address this issue, mathematical wavelet transforms have been tested, and key recognition has been implemented using the inference test of a deep learning model based on a Temporal Convolutional Network (TCN). The novelty of the proposed pipeline lies in its dynamic audio analysis and keystroke recognition, which splits the wave based on audio signal peaks generated by key presses. This approach enables an attack in real-world conditions without knowing the exact number of keystrokes typed by the user. Experimental results for the proposed pipeline show a peak accuracy of 98.3%.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 24498-24514
Open AccessA New Pipeline for Snooping Keystroke Based on Deep Learning Algorithm
This research focuses on the vulnerability issues related to keystroke logging on a physical computer keyboard, known as Snooping Keystrokes. This category of attacks occurs recording an audio track with a smartphone while typing on the keyboard, and processing the audio to detect individual pressed keys. To address this issue, mathematical wavelet transforms have been tested, and key recognition has been implemented using the inference test of a deep learning model based on a Temporal Convolutional Network (TCN). The novelty of the proposed pipeline lies in its dynamic audio analysis and keystroke recognition, which splits the wave based on audio signal peaks generated by key presses. This approach enables an attack in real-world conditions without knowing the exact number of keystrokes typed by the user. Experimental results for the proposed pipeline show a peak accuracy of 98.3%.
- Open Access
- 24 October 2024
- Published by Elsevier in Intelligence-Based Medicine
- Vol. 10
Temporal convolutional network on Raman shift for human osteoblast cells fingerprint analysis
- 24 October 2024
- Published by Elsevier in Intelligence-Based Medicine
- Vol. 10
Open AccessTemporal convolutional network on Raman shift for human osteoblast cells fingerprint analysis