👋 Jesús F. Cevallos

🧠 Postdoc Researcher & Lecturer @ University of Insubria

🔬 Research Focus

Algorithmic Reasoning Inductive Biases for Cybersecurity
Human-centred Language Models

Profile

Jesús F. Cevallos M. received his Ph.D. in Computer Science Engineering from Sapienza University (Rome) in 2022. He now holds a postdoctoral researcher position at the University of Insubria (Varese, Italy).

His main research interests are industrial/ethical applications of Deep Learning with a special focus on Natural Language Processing and Neural Algorithmic Reasoning.

Research Group

Advisor: Prof. Alessandra Rizzardi

Board: Prof. Sabrina Sicari, Prof. Alberto Coen-Porisini

Academic Services

Program Committee Member (TPC):

  • International Conference on Responsible, Generative, and Explainable AI (ResGenXAI), 2025
  • 7th International Workshop on Cyber-Security in Software-defined and Virtualized Infrastructures (SecSoft 25), 2025

Reviewer for Conferences:

  • International Joint Conference on Artificial Intelligence (IJCAI-26), 2026
  • International Joint Conference on Artificial Intelligence (IJCAI-25), 2025
  • International Conference on Responsible, Generative, and Explainable AI (ResGenXAI), 2025
  • 7th International Workshop on Cyber-Security in Software-defined and Virtualized Infrastructures (SecSoft 25), 2025
  • International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob'20), 2024

Reviewer for Journals:

  • Computer Networks
  • Computers & Security
  • Pervasive and Mobile Computing
  • Transactions on Emerging Telecommunications Technologies
  • Internet Technology Letters
  • Journal of Information Assurance and Security
  • IoT, Electronics, Symmetry, Eng, Applied Sciences, Sensors, Information
  • International Journal of Computer Theory and Engineering

🎯 Recent Publications

🛡️

Ethical AI

Open-Ethical AI: Advances in Human-Centric NLMs

ACM Computing Surveys, Vol 57(4), 2024

Sabrina Sicari, Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Alberto Coen-Porisini

Survey on open-source ethical AI developments

Ethical Treatment of Language Models Against Harmful Inference-Time Interventions

Engineering Applications of Artificial Intelligence (Elsevier), Volume 172, 2026

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

Can LLMs resist harmful representation engineering?

⚙️

Neural Algorithmic Reasoning for Cybersecurity

SmartVille: A Framework for Realistic Deep Learning-Based Online Network Intrusion Detection

Journal of Network and Systems Management, 2026

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

TIGER: An Open-Source Cyber-Threat Intelligence Game Environment for Reinforcement Learning

IEEE Transactions on Network and Service Management, 2026

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

SereWay: Toward SEcurity and REliability Benchmarking for the RailWAY IIoT

Journal of Network and Systems Management, 2026

Open-FARI: An Open-Source Testbed for Federated Anomaly Detection in the Railway IIoT

IWCMC, 2025

ASAP: Automatic Synthesis of Attack Prototypes, an online-learning, end-to-end approach

Computer Networks (Elsevier), 2024

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

End-to-end online-learning approach using the relational-bottleneck Inductive Bias for Prototype attack synthesis from raw network traffic.

NERO: NEural algorithmic reasoning for zeRO-day attack detection in the IoT: A hybrid approach

Computers & Security (Elsevier), 2024

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

Extreme value theory, the algorithmic way!

Deep Reinforcement Learning for Intrusion Detection in Internet of Things: Best Practices, Lessons Learnt, and Open Challenges

Computer Networks (Elsevier), 2023

Jesus Fernando Cevallos Moreno, Alessandra Rizzardi, Sabrina Sicari, Alberto Coen-Porisini

HERO: From High-dimensional network traffic to zERO-Day attack detection

Computer Networks, 2025

Full firepower of the Neural Algorithmic Reasoning paradigm for zero-day attack detection!

🧪

Inductive Biases for Cybersecurity

ACID: beta-testing ACtive Inference for active cyber-Defence

TechRXiv Preprint, 2025

A powerful optimal-control framework needs a powerful task to be tested against!

ASAP: Automatic Synthesis of Attack Prototypes

Computer Networks (Elsevier), 2024

End-to-end online-learning approach using the relational-bottleneck Inductive Bias for Prototype attack synthesis from raw network traffic.

Deep Reinforcement Learning for Intrusion Detection in Internet of Things: Best Practices, Lessons Learnt, and Open Challenges

Computer Networks (Elsevier), 2023

🚀

Collaborations

IoT-driven blockchain to manage the healthcare supply chain and protect medical records

Future Generation Computer Systems (Elsevier), 2024

Alessandra Rizzardi, Sabrina Sicari, Jesus F. Cevallos M., Alberto Coen-Porisini

RailRED: A Node-RED-Based Framework for Modeling Train Control Management Systems

WiMob, 2024

Alessandra Rizzardi, Raffaele Della Corte, Jesus Fernando Cevallos Moreno, Vittorio Orbinato, Simona De Vivo, Sabrina Sicari, Domenico Cotroneo, Alberto Coen-Porisini

Learning at the nano-scale: how to dynamically protect data in nano-network transmissions

Annals of Telecommunications, 2026

Alessandra Rizzardi, Sabrina Sicari, Luigi Alfredo Grieco, Giuseppe Piro, Jesus F. Cevallos-Moreno, et al.

Deep RL for vCDN Service Function Chain Deployment

Future Internet (MDPI), 2021

Online optimization for live-streaming CDNs using dueling DDQN.

Cevallos M. J. F., R. Sattler, R. P. Caulier C., L. R. Celsi, A. Sánchez Rodríguez, and M. Mecella

DeepReGraph: Heterogeneous Graph Learning for Gene Regulation

F1000Research, 2022

Deep learning approach for understanding embryonic regulatory mechanisms through graph representation learning.

Cevallos. M., J. F., P. Zarrineh, A. Sánchez., and M. Mecella

SERENA-IIoT: Secure and Reliable IoT Systems

Collaborative Research Project

Collaborative research on secure and reliable IoT systems.

HR-specific NLP for the Homogeneous Classification of Declared and Inferred Skills

Applied Artificial Intelligence, 2022

L.R. Celsi, J. F. Cevallos M., F. Kieffer, V. Paduano

Deep Learning Applications over Heterogeneous Networks: from Multimedia to Genes

Ph.D. Thesis Dissertation, Sapienza University of Rome, 2022

🎓 Education

Ph.D. in Computer Science Engineering

Sapienza University of Rome, 2022

Master's in Computer Science Engineering

Tor Vergata University of Rome, 2018

Bachelor's in Computer Science Engineering

Tor Vergata University of Rome, 2015

🧑‍🏫 Teaching Experience

Lecturer

Probability and Statistics for Computer Science

Insubria University, Varese, 2023/2024

Bachelor's degree in Computer Science

Advanced Coding Tools and Methodologies

Politecnico di Milano, 2022/2023

Master's degree in Music and Acoustic Engineering

📚 Guest Lectures

Immunisation of Language Models

Pontificia Universidad Católica del Ecuador, Sede Santo Domingo, 2026

Invited keynote speaker at the EHIC Academic Week, School of Habitat, Infrastructure and Creativity (Academic Period 2026-01)

Active Inference — Digital Workshop

Pontificia Universidad Católica del Ecuador, Sede Santo Domingo, 2025/2026

Digital Workshop for the EHIC Academic Week, School of Habitat, Infrastructure and Creativity

Active Inference

Universidad Técnica Particular de Loja (Ecuador), 2026

Seminar held within the Machine Learning course, Bachelor's degree in Computer Science

Introduction to Machine Learning

Pontificia Universidad Católica del Ecuador, Sede Ibarra, 2026

Seminar held within the Programming course, Bachelor's degree in Computer Science

How to Artificially Program an Intelligence

Insubria University (Italy), 2025

Bachelor's degree course on Legal Computer Science

Educating Ourselves to Educate in the Age of AI

Università degli Studi dell'Insubria (Italy), 2026

Seminar held within the course "Artificial Intelligence in Community Work," Master's Program for Intercultural Community Educators (EDC)

AI and Cyber-security

Insubria University (Italy), 2023

Bachelor's degree course on Legal Computer Science

AI Working Principles: Advantages and Disadvantages

Insubria University (Italy), 2024

Bachelor's degree course on Legal Computer Science

An Extremely Gentle Introduction to Active Inference

Insubria University (Italy), 2025

Bachelor's degree course on Legal Computer Science

Inductive Biases for Meta-Learning

Federico II University (Italy), 2024 - A Research Retrospective

Machine Learning Meets the Internet of Things

Insubria University (Italy), 2023

Guest Lecture on the Innovative IoT PhD course

🔬 Research Interests

AI-based Cyber-Security Applications for the IoT

Deep Learning-based Cyber-security for the IoT
Neural Algorithmic Reasoning
Ethical AI
Deep Reinforcement Learning
Graph Representation Learning

🚀 Projects

SERENA-IIoT: Secure and Reliable IoT Systems

Collaborative research on secure and reliable IoT systems.

SERENA-IIoT Project

💬 Contact

I'm always open to discussing research collaborations, interesting AI problems, or just chatting about the latest developments in deep learning and cybersecurity.

University of Insubria
Department of Theoretical and Applied Science (DiSTA)
Padiglione Rossi, Via Ottorino Rossi 9
21100 Varese (VA), Italy