Security, Human Awareness, and Risk Mitigation in AI-driven Systems (Naples, Italy)

Security, Human Awareness, and Risk Mitigation in AI-driven Systems (SHIELD-AI 2026)

📍 Naples, Italy
📅 7–11 September 2026
🌐 https://shield-ai2026.github.io/ecmlpkdd/

SHIELD-AI 2026 is an interdisciplinary workshop focused on AI risk management, human–AI interaction, and human-centered cybersecurity in adversarial and security-critical environments. The workshop will be held in conjunction with ECML PKDD 2026 (https://ecmlpkdd.org/2026/).


About the workshop

Artificial Intelligence systems are increasingly embedded in everyday applications and critical infrastructures. While they provide significant benefits, they also introduce systemic risks related to vulnerabilities, bias, complex integrations, and human–AI interaction dynamics.

At the same time, cyber threats are evolving toward the cognitive domain, exploiting human behavior, trust mechanisms, and social dynamics. Attacks such as phishing, social engineering, and disinformation campaigns highlight the need for human-centered approaches to cybersecurity.

SHIELD-AI 2026 aims to bring together researchers and practitioners from machine learning, cybersecurity, and human-centered computing to advance methods for identifying, modeling, and mitigating risks in AI-enabled socio-technical systems.


Topics of interest include (but are not limited to):

  • Risk identification and modeling in AI-driven systems
  • Human–AI interaction risks, trust, and decision-making
  • Human-centered cybersecurity and social cyber attacks
  • ML and knowledge discovery for cyber threat detection
  • NLP and LLMs for malicious content analysis
  • Graph learning and knowledge graphs for cyber ecosystems
  • Bias, robustness, and adversarial machine learning
  • Explainable and trustworthy AI for security-critical systems
  • Generative AI for attack and defense scenarios
  • Runtime monitoring and adaptive risk mitigation
  • Human behavioral data analysis
  • Privacy, data protection, and cyber threat intelligence
  • Human-in-the-loop methods for risk assessment

Organizing Committee

  • Gaetano Cimino (University of Salerno, Italy)
  • Stefano Cirillo (University of Salerno, Italy)
  • Miriana Calvano (University of Bari Aldo Moro, Italy)
  • Giuseppe Desolda (University of Bari Aldo Moro, Italy)
  • Idio Guarino (University of Bologna, Italy)
  • Pantaleone Nespoli (University of Murcia, Spain)
  • Eliana Pastor (Polytechnic University of Turin, Italy)
  • Gaetano Perrone (University of Naples Federico II, Italy)
  • Roberta Presta (UniversitĂ  degli Studi Suor Orsola Benincasa, Italy)
  • Giancarlo SperlĂ­ (University of Naples Federico II, Italy)
  • Serena Tardelli (IIT-CNR, Pisa, Italy)

We would greatly appreciate it if you could share this call with interested colleagues and communities.

For more information, please visit:
👉 https://shield-ai2026.github.io/ecmlpkdd/

We look forward to your contributions!

Best regards,
The SHIELD-AI 2026 Organizing Committee


You can leave a response, or trackback from your own site.

Leave a Reply

Design by 2b Consult