Overview

Generative Artificial Intelligence (GenAI) is transforming the landscape of digital content creation—from software and code generation to text, images, and synthetic data. These technologies enableautomation at scale and open new opportunities across sectors such as software engineering,cybersecurity, healthcare, and education. However, as GenAI systems become increasinglydeployed in mission-critical and sensitive domains, their inherent vulnerabilities raise pressingconcerns regarding security, dependability, and ethical use.DSGenAI-2025 is an international workshop dedicated to exploring the challenges andadvancements in building dependable and secure GenAI systems. The workshop will bring togetherresearchers, practitioners, and policymakers from diverse disciplines to examine the threats andrisks posed by GenAI technologies and develop strategies to improve their robustness, reliability,and trustworthiness.Through peer-reviewed paper presentations and interactive sessions, the workshop will provide aplatform to share knowledge, foster collaboration, and shape the future of secure GenAI researchand developmen

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. We invite original research papers, position papers, tool demonstrations, and case studies on the following topics:

List of Topics

We invite original research papers, position papers, tool demonstrations, and case studies ontopics including, but not limited to:

• Secure training and fine-tuning of generative AI models to prevent adversarial manipulationand backdoor attacks.
• Adversarial attacks and defenses against GenAI models and outputs, including evasion,poisoning, and prompt injection techniques.
• Dependability and fault tolerance in GenAI pipelines, focusing on robust modelperformance in dynamic or degraded environments.
• Explainability and interpretability of AI-generated content to support human oversight andtrust.
• Secure prompt engineering, mitigation of prompt injection, prompt leakage, and maliciousoutput risks.
• Formal methods for verification and validation of AI-generated artifacts, especially codeand scripts.
• Privacy-preserving GenAI techniques, including federated learning, data minimization, and synthetic data generation.
• Ethical, legal, and regulatory compliance in GenAI system development and deployment.
• Benchmarking and evaluation metrics for assessing GenAI system security, safety, anddependability.

Organizing committee

• Prof. Yasir Malik, Bishop’s University, Canada
• Prof. Fehmi Jaafar, Université du Québec à Chicoutimi (UQAC), Canada

Venue

The conference will be held in AbuDhabi, UAE on the 20th October 2025.

Contact

All questions about submissions should be emailed to ymalik@ubishops.ca