Institution profile

Universidade Estadual de Campinas

Academic institutionsouthamerica · br
Official website
Research library200linked papers
Opportunities0open roles
Selected work

Representative Papers

Degree-Preserving Gödel Logics with an Involution: Intermediate Logics and (Ideal) Paraconsistency

Jan 13, 2026Outstanding Contributions to Logic

This study investigates intermediate logics situated between degree-preserving Gödel fuzzy logic with involution and classical propositional logic, focusing on their paraconsistent behavior relative to involutive negation in the finite-valued setting. By introducing “saturated paraconsistency”—a notion strictly weaker than ideal paraconsistency—and combining tools from algebraic logic, the classification of intermediate logics, and finite-valued fuzzy logic, the work fully characterizes the boundaries of all ideal and saturated paraconsistent logics lying between the n-valued Gödel involutive logic and classical logic. Furthermore, it identifies a broad class of saturated paraconsistent logics within intermediate systems of finite-valued Łukasiewicz logic.

6 citations1 influentialRead paper

Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning

Jun 26, 2024International Symposium on Computers and Communications

To address the challenge of simultaneously ensuring privacy preservation and defending against model poisoning attacks in federated learning, this paper proposes a collaborative defense framework that jointly guarantees privacy, security, and robustness. Methodologically, it integrates secure aggregation to protect client data privacy; introduces a reputation-based dynamic participation mechanism coupled with model divergence analysis to detect malicious clients; and incorporates robust aggregation strategies—including Trimmed Mean and Median—along with post-attack training recovery capabilities. Evaluated in a Docker-based distributed simulation environment, the framework achieves stable convergence under model poisoning attacks, outperforms FedAvg and Power-of-Choice in convergence speed, and significantly enhances system security and robustness. The key innovation lies in the first holistic integration of reputation assessment, secure aggregation, and elastic recovery mechanisms—thereby unifying privacy protection, attack resilience, and training efficiency.

2 citationsRead paper

Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks

Feb 07, 2025

This study investigates the capability of large language models (LLMs) to generate trustworthy free-text explanations in zero-shot settings, with a focus on out-of-distribution (OOD) generalization. We introduce the first large-scale, cross-task benchmark for explanation generation, covering 19 OOD datasets across natural language inference, fact verification, and summary hallucination detection. Our method employs fine-tuned T5-Large and OLMo-7B models integrated with a few-shot selection strategy and a novel reference-free evaluation framework—including the proposed Acceptability score—assessing explanation faithfulness, coherence, and informativeness. Key findings include: (i) a small number of high-quality annotations substantially improves OOD explanation quality; (ii) explanation quality strongly correlates with prediction accuracy; (iii) the Acceptability score achieves a Pearson correlation of 0.82 with human judgments; and (iv) data source quality exerts a significantly greater influence on OOD performance than sampling strategy.

1 citations1 influentialRead paper

Trigger Optimization and Event Classification for Dark Matter Searches in the CYGNO Experiment Using Machine Learning

Jan 28, 2026

This work addresses the challenges of efficient real-time triggering, compression, and background suppression in high-resolution sparse optical imaging within the CYGNO experiment. To this end, two novel approaches are proposed: first, an unsupervised online compression framework based on a convolutional autoencoder that extracts regions of interest (ROIs) via reconstruction residuals, achieving fully unsupervised real-time ROI identification for the first time in CYGNO—retaining 93.0% of signal intensity while discarding 97.8% of background pixels with only 25 ms inference latency; second, the application of the weakly supervised Classification Without Labels (CWoLa) method to mixed data, which successfully identifies compact, circular nuclear recoil events and achieves performance approaching the theoretical optimum.

1 citationsRead paper
Recent publications

Latest Papers