Saulo Roberto dos Santos

Saulo Roberto dos Santos

Auto-generated profile, based on publicly available information

Saulo Roberto dos Santos

Computing Institute, Federal University of Alagoas

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 February 2026
Verified
Book Chapter
Closed access
GAGabriel Vitorino de Andrade
Gabriel Vitorino de Andrade
SSSaulo Roberto dos Santos
Saulo Roberto dos Santos
ISItallo Patrick Castro Alves da Silva
Itallo Patrick Castro Alves da Silva
EPEmanuel Adler Medeiros Pereira
Emanuel Adler Medeiros Pereira
EBErick de Andrade Barboza
Erick de Andrade Barboza

11 June 2026 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
EPEmanuel Adler Medeiros Pereira
Emanuel Adler Medeiros Pereira
EBErick de Andrade Barboza
Erick de Andrade Barboza
ÍAÍcaro Bezerra Queiroz de Araújo
Ícaro Bezerra Queiroz de Araújo
SSSaulo dos Santos
Saulo dos Santos
GAGabriel de Andrade
Gabriel de Andrade
AMallan martins
allan martins
TinyML enables the deployment of machine learning models on low-power embedded devices, offering energy-efficient solutions for real-world applications. However, TinyML faces significant challenges due to strict memory, processing, and energy constraints, making the implementation of robust and scalable models particularly difficult. Robustness in this context refers to the ability of models to maintain stable performance under adversarial conditions, sensor noise, and environmental variability, which makes it an essential requirement for reliable deployment in practical scenarios. This study conducts a systematic literature review to examine how robustness is assessed in TinyML, analyzing key factors such as input data types, accessibility of the dataset, real vs. simulated data usage, application domains, evaluated robustness types, hardware constraints, and commonly used performance metrics. The findings show a strong preference for sensor-based inputs, public and real-world datasets, and a focus on noise-related robustness challenges. Memory efficiency stands out as the main hardware constraint, while accuracy is the most used evaluation metric, reflecting the dominance of classification tasks in TinyML research. These insights provide a structured overview of current trends and reveal key gaps in TinyML robustness research, such as the lack of standardized benchmarking frameworks and the need for more advanced adversarial defense mechanisms tailored to low-power environments. They also highlight opportunities for integrating federated and physics-informed learning approaches, promoting the development of more secure, efficient, and resilient embedded machine learning systems.

1 October 2026
Verified
Book Chapter
Closed access
PDF file
DNde Oliveira Neto
de Oliveira Neto
JFJosé Félix
José Félix
DAde Andrade
de Andrade
GVGabriel Vitorino
Gabriel Vitorino
EBErick de Andrade Barboza
Erick de Andrade Barboza
BFBaldoino Fonseca
Baldoino Fonseca