Advancing European Border Security: EURMARS Journey from Innovation to Real-World Impact

Written by george.armagos on 29 September 2025. Posted in Article.

As Europe continues to face evolving security challenges across its maritime and land borders, the EURMARS project has emerged as a leading example of how technological innovation and cross-border cooperation can strengthen the continent’s resilience. Funded under the Horizon Europe programme, EURMARS – An advanced surveillance platform to improve the EURopean Multi-Authority bordeR Security efficiency and cooperation, brings together 18 partners from 13 countries, uniting expertise from research, industry, SMEs and end-user communities.

From Vision to Deployment

Launched in 2022, EURMARS set out to design, develop, and validate a multi-authority surveillance platform capable of integrating data from satellites, unmanned vehicles, high-altitude platforms, and ground-based sensors. By combining these sources through AI-driven data fusion and advanced analytics, the platform provides a shared operational picture that enhances situational awareness and supports timely, informed decision-making across European border agencies.

The project’s development was structured around a series of Living Labs and Pilot Demonstrations, which allowed users to test technologies under realistic operational conditions. Early Living Labs in Varna, Bulgaria, focused on interoperability and real-time vessel detection. These were followed by major pilot demonstrations in Cyprus, the United Kingdom, and Bulgaria, where the EURMARS platform was tested in live scenarios such as search and rescue operations and maritime law enforcement missions.

Collaboration and Knowledge Exchange

Throughout its three-year duration, EURMARS has actively contributed to the European research community through participation in key events such as RISE-SD 2024, HEMUS 2024, the CERIS Joint Demonstration Event, and the Security Research Event 2025. These platforms enabled the consortium to engage with EU agencies, policymakers, and practitioners, promoting collaboration and the exchange of best practices in security research and innovation.

Looking Ahead

As EURMARS reaches its conclusion in 2025, its achievements extend beyond the technological domain. The project has laid a foundation for a sustainable, interoperable, and ethically responsible surveillance framework, demonstrating that European cooperation can deliver tangible results in safeguarding borders. Its tested technologies, validated frameworks, and collaborative networks will continue to inform future research, policy, and market uptake – reinforcing EURMARS’ legacy as a model for innovation in European security.

Building Trust in Border Technology – The Science of Systematic Validation

Written by george.armagos on 26 September 2025. Posted in Article.

Building Trust in Border Technology
The Science of Systematic Validation

Systems Engineering | European Security Research | Validation Methodologies

European researchers have developed revolutionary frameworks for ensuring that border surveillance systems actually work in the real world. These scientific approaches to validation are transforming how we build trust in critical security technology.

The Assurance Case Revolution

For decades, security system validation relied on simple checklists and compliance matrices. European researchers have introduced a more sophisticated approach: the “assurance case” a documented body of evidence that provides a convincing and valid argument that a system is adequately built for its intended purpose.

Breakthrough Concept: Rather than just checking boxes, assurance cases require explicit arguments connecting evidence to claims, creating a transparent reasoning process that can be audited and verified.

This approach represents a fundamental shift from “does it meet standards?” to “does it actually work for its intended purpose?” The difference is crucial in complex border security environments where standard compliance doesn’t guarantee operational effectiveness.

The Hierarchical Framework for System Validation

The assurance case methodology organizes evidence in a hierarchical structure that moves from abstract goals to concrete proof. This systematic approach ensures that every aspect of system performance is rigorously validated.

Top Level: Mission Goals

What is the system supposed to achieve? Enhanced border security, improved threat detection, better resource allocation.

Middle Level: System Claims

Specific claims about system capabilities: “The system can detect small vessels at 95% accuracy” or “The interface reduces decision time by 30%.”

Evidence Level: Concrete Proof

Actual test results, operational data, risk assessments, user feedback, and validation studies that support each claim.

This hierarchical structure ensures that high-level goals are systematically connected to real-world evidence. Every claim must be supported by tangible proof, creating a chain of reasoning that can be examined and validated by independent experts.

Requirements Reuse: Accelerating Innovation

One of the most significant innovations emerging from European research is the systematic reuse of requirements across different border security projects. This approach addresses a critical challenge in European security research: how to build upon previous work rather than starting from scratch with each new initiative.

Case Study: Multi-Project Knowledge Transfer

Analysis of seven major EU-funded border management projects revealed that requirements reuse could have accelerated development by 40% while improving consistency across related systems.

Project A Requirements

→

Knowledge Base

→

Project B Adaptation

→

Enhanced System

This flow represents a paradigm shift from isolated project development to continuous knowledge building and refinement across the European security research ecosystem.

The benefits extend beyond efficiency. Requirements reuse ensures that lessons learned from operational deployment are captured and applied to future systems. When border guards identify problems or suggest improvements, this knowledge can be systematically incorporated into new projects.

Scientific Benefits of Systematic Validation

The research reveals multiple scientific advantages of these new validation approaches:

🔍

Enhanced Transparency

Clear reasoning chains make system capabilities and limitations visible to all stakeholders

🎯

Better Targeting

Validation focuses on operational effectiveness rather than just technical specifications

🔄

Continuous Improvement

Systematic knowledge transfer accelerates learning and innovation across projects

⚖️

Legal Defensibility

Documented evidence and reasoning provide legal protection for system operators

🤝

Stakeholder Confidence

Transparent validation builds trust among operators, managers, and oversight bodies

📈

Performance Optimization

Evidence-based approach enables continuous system performance improvement

Real-World Implementation Success

European border security agencies have begun implementing these validation frameworks with remarkable results. The assurance case approach has been particularly successful in maritime border surveillance, where complex systems must operate reliably in challenging environments.

The methodology has proven especially valuable for systems incorporating artificial intelligence and machine learning. Traditional validation approaches struggle with AI systems that learn and adapt over time. Assurance cases provide a framework for validating not just the initial system, but its ongoing performance and evolution.

Operational Impact: Agencies using systematic validation report 60% fewer system failures and 45% faster problem resolution when issues do occur.

Implications for Future Security Technology

The research has profound implications for how we approach security technology development. Rather than focusing solely on technical innovation, we must equally invest in validation innovation, the science of ensuring that technology actually works as intended.

This shift represents a maturation of the security technology field. Just as aviation moved from trial-and-error to systematic safety engineering, border security is evolving from technology-centric to effectiveness-centric development approaches.

The European experience demonstrates that the most advanced technology is worthless without systematic validation. Conversely, even modest technology can be highly effective when properly validated and integrated into operational workflows.

Policy and Regulatory Implications

These validation frameworks are influencing European policy and regulation. The European Commission now requires assurance case approaches for major security system procurements, recognizing that systematic validation is essential for public accountability.

The approach also addresses growing concerns about AI transparency and accountability. Assurance cases provide a framework for explaining and defending AI-driven decisions, which is crucial for legal and ethical compliance in security applications.

A New Foundation for Trust

The European research on systematic validation represents a fundamental advancement in how we approach security technology. By moving beyond simple compliance checklists to rigorous, evidence-based validation, we can build systems that deserve the trust placed in them.

This scientific approach to validation provides the foundation for the next generation of border security technology systems that are not only technologically sophisticated but also operationally proven, legally defensible, and worthy of public trust.

As border security challenges continue to evolve, these validation frameworks provide the scientific rigor needed to ensure that our technological responses are effective, reliable, and accountable.

Leveraging Context-Aware Microtasks and Feedback Loops to Improve Decision Support in Border Management Operational Procedures

Written by george.armagos on 17 July 2025. Posted in Article.

In today’s interconnected world, European border security faces increasingly complex challenges. Issues such as illegal migration, human and drug trafficking, and other transnational crimes continue to test the capabilities of national and regional authorities. To respond effectively, the European Union has invested in advanced technological projects like EURMARS, which aim to improve coordination among multiple agencies. By combining data from satellites, drones, high-altitude platforms, and ground sensors, EURMARS creates a unified surveillance system that strengthens monitoring and situational awareness across Europe’s borders.

A key part of this framework is the Decision Support System (DSS), which helps officers manage security incidents more efficiently. Instead of simply alerting users to threats, the DSS offers practical, step-by-step guidance that aligns with existing Common Operational Procedures (COPs). This guidance is delivered in the form of context-aware microtasks small, clear actions tailored to each situation, such as confirming vessel identity or assessing environmental risks. These microtasks help officers follow procedures more consistently and make better decisions during fast-moving operations.

The DSS also integrates Natural Language Processing (NLP) to analyze user feedback and learn from past experiences. During and after operations, officers can provide comments or rate the usefulness of the system’s recommendations. NLP tools then interpret this input to refine and prioritize microtasks for future use. Over time, the system becomes smarter and more adaptive, ensuring that it continuously improves based on real operational feedback. Importantly, the DSS does not replace human decision-making; rather, it supports officers by providing clearer guidance and reducing uncertainty.

Field tests conducted in Cyprus, the United Kingdom, and Bulgaria have shown promising results. As users interacted with the DSS, the system generated new and more effective microtasks, improving coordination between agencies and helping officers act with greater confidence. By integrating advanced AI technologies with human expertise, EURMARS demonstrates how intelligent systems can enhance security, strengthen cooperation, and support faster, more reliable decision-making in border management operations.

Beyond Algorithms: Human-AI Partnership in Border Security

Written by george.armagos on 21 April 2025. Posted in Article.

Beyond Algorithms: Human-AI Partnership in Border Security

Why Human-AI Partnership Matters in Border Security

AI Research | Human-System Interaction | Security Technology Innovation

Groundbreaking European research reveals that the most advanced AI border security systems fail without proper consideration of human factors. The future of border protection lies not in replacing humans, but in creating powerful partnerships between artificial intelligence and human expertise.

The AI Performance Paradox

For years, developers assumed that creating more accurate AI algorithms would automatically lead to better border security. They were wrong. Recent comprehensive studies across 40 different research projects reveal a startling paradox: technically perfect AI systems can actually reduce overall security effectiveness when human factors are ignored.

Critical Finding: AI system accuracy metrics like precision and recall don’t predict operational success in real-world border security scenarios.

The research demonstrates that border guards operating AI-enhanced systems face unique challenges. They must make life-critical decisions based on AI recommendations while maintaining situational awareness in complex, rapidly evolving environments. Systems designed without considering this human element create cognitive overload rather than enhanced capability.

The Three Pillars of Situational Awareness

European researchers have developed a revolutionary framework for understanding how humans and AI can work together effectively. Based on established psychological principles, this three-level approach transforms how we think about AI integration in security systems.

1. Perception: AI systems excel at processing vast amounts of sensor data, detecting patterns, and identifying anomalies that humans might miss. However, humans provide contextual understanding and can distinguish between routine variations and genuine threats.

2. Comprehension: While AI can classify and categorize information, humans excel at understanding the meaning and implications of complex situations. The partnership combines AI’s processing power with human judgment and experience.

3. Projection: Humans are superior at anticipating future scenarios and understanding behavioral patterns. AI can support this by providing data-driven predictions, but human expertise remains central to strategic decision-making.

The OODA Loop Revolution

The research adapts a proven military decision-making model the OODA loop (Observe, Orient, Decide, Act) to border security contexts. This framework provides a structured approach to human-AI collaboration that enhances rather than replaces human decision-making.

Traditional AI Approach

• AI makes autonomous decisions
• Humans serve as backup systems
• Focus on technical accuracy
• Limited human understanding of AI reasoning

Human-AI Partnership

• AI enhances human decision-making
• Humans maintain control and oversight
• Focus on operational effectiveness
• Transparent AI reasoning processes

This approach recognizes that in security-critical domains, human oversight isn’t just desirable—it’s essential. The responsibility for decisions that affect human lives cannot be delegated to algorithms alone.

Scientific Breakthroughs in Human-AI Systems

The European research reveals several key insights that are transforming how we approach AI in border security:

Transformative Research Findings

The Complexity Challenge

AI systems with multiple algorithms can create architectures so complex that even expert users struggle to understand them. This complexity undermines trust and effective utilization.

The Human-in-the-Loop Imperative

In security domains, human operation is required by law and ethics. “Man-out-of-the-loop” designs are not viable options, making human-AI collaboration essential rather than optional.

The Time-Critical Factor

Border security operations are characterized by time-critical decision-making under pressure. AI systems must enhance rapid decision-making rather than introduce delays or confusion.

The Responsibility Gap

While AI can provide recommendations and analysis, human authorities bear legal and moral responsibility for decisions. Systems must support this accountability structure.

Practical Applications and Results

The research demonstrates concrete benefits of human-AI partnership approaches in real border security scenarios:

Enhanced Situational Awareness: AI systems that work with human cognitive processes rather than against them significantly improve operational awareness and threat detection.

Reduced False Alarms: Human oversight helps filter AI-generated alerts, reducing false positives that can overwhelm operators and lead to alert fatigue.

Improved Decision Quality: The combination of AI data processing and human judgment produces better decisions than either could achieve alone.

Increased Operator Confidence: When operators understand and trust AI systems, they’re more likely to use them effectively and appropriately.

The Future of Border Security AI

This research points toward a future where AI and human intelligence work in seamless partnership. The goal isn’t to create autonomous border security systems, but to develop AI that makes human operators more effective, more accurate, and more capable.

The implications extend beyond border security to any domain where critical decisions must be made under pressure with incomplete information. The principles of human-AI partnership developed in this research provide a roadmap for responsible AI deployment in high-stakes environments.

Looking Ahead: The most successful border security systems of the future will be those that best combine artificial intelligence with human wisdom, creating partnerships that are more powerful than either could be alone.

A New Paradigm for Security Technology

The European research on human-AI partnership in border security represents a fundamental shift in how we approach technology development for critical applications. Rather than pursuing autonomous systems that replace human judgment, we should focus on creating partnerships that enhance human capabilities.

This human-centered approach to AI development offers the best path forward for creating border security technology that is not only technologically advanced but also operationally effective, ethically sound, and genuinely useful to the people who depend on it every day.

How Human-Centered Design is Transforming Maritime Surveillance and Revolutionising Border Security

Written by George Mourkousis on 14 March 2025. Posted in Article.

Keywords: Scientific Analysis | Border Management Innovation | European Research

Recent research reveals a fundamental shift in how border surveillance systems are designed and implemented. Rather than starting with technology, successful projects begin with the people who will use these systems every day.

The Human Element in High-Tech Security

For decades, border security technology development followed a predictable pattern: engineers created sophisticated systems and expected border guards to adapt. The results were often expensive failures—technology that worked perfectly in laboratories but failed in real-world conditions.

Recent research from Finland’s VTT Technical Research Centre demonstrates why this approach was fundamentally flawed. Their work on maritime border surveillance reveals that the most advanced technology becomes useless if it doesn’t align with human operational needs.

Key Insight: The most sophisticated border surveillance system is only effective when border guards can actually use it effectively in high-pressure situations.

Participatory Design: A Game-Changing Approach

The European research introduces “participatory design”—a methodology that flips traditional development on its head. Instead of technology driving the process, real users drive the requirements from day one.

This approach recognizes that maritime border security involves complex coordination between numerous agencies: border guards, coast guards, customs officials, fisheries control, and environmental protection services. Each has unique needs and operational constraints.

How It Works in Practice

The research demonstrates that participatory design involves continuous dialogue between developers and end-users throughout the development process. Border guards don’t just test finished products—they help shape every aspect of the system from initial concepts to final implementation.

This iterative process ensures that technological capabilities align with operational realities. For example, a surveillance system might have perfect technical specifications, but if it requires complex procedures that slow down emergency responses, it fails the ultimate test of operational effectiveness.

Real-World Impact and Benefits

The European studies reveal several transformative benefits of this human-centered approach:

Documented Advantages

Enhanced Technology Acceptance: When users help design systems, they’re more likely to embrace and effectively use the technology
Reduced Development Risk: Early user feedback prevents costly late-stage redesigns
Improved Operational Fit: Systems align with actual workflows rather than theoretical processes
Faster Implementation: Reduced training time and smoother adoption curves

The research shows that this approach is particularly critical in security domains where split-second decisions have life-or-death consequences. Border guards operating in challenging maritime environments need technology that enhances their capabilities without adding cognitive burden.

Scientific Innovation and Methodology

The breakthrough in this research lies not just in the outcomes, but in the rigorous scientific methodology developed. The researchers created systematic frameworks for capturing and integrating user requirements across diverse stakeholder groups.

This represents a significant advancement over traditional requirements gathering, which often relies on static documentation and limited user consultation. The participatory approach creates dynamic feedback loops that continuously refine system design.

Scientific Contribution: The research provides replicable methodologies for complex, multi-stakeholder technology development in high-stakes environments.

Implications for Future Border Technology

The implications extend far beyond maritime surveillance. The methodologies developed in this research provide a template for any complex security technology development involving multiple stakeholders and high-stakes operations.

As border security challenges become increasingly complex—involving irregular migration, transnational crime, and environmental protection—the need for well-designed, user-centered technology becomes more critical. This research provides the scientific foundation for meeting that challenge.

The European experience demonstrates that successful border security technology isn’t just about technical capabilities—it’s about creating systems that work for the people who depend on them every day.

Looking Forward

The research from European border security experts represents a paradigm shift in how we approach technology development for critical security applications. By putting human needs at the center of the design process, we can create systems that are not only technologically advanced but also operationally effective.

This human-centered approach offers a path forward for developing border security technology that actually works in the real world—technology that enhances rather than complicates the critical work of protecting our borders.

*This analysis is based on peer-reviewed research from European border security experts and represents current scientific understanding in the field.

An Ethics by Design approach to border security

Written by george.armagos on 8 May 2024. Posted in Article.

Article by
Trilateral Research Ltd.

Security risks and threats in the maritime domain are becoming increasingly more complex, with significant increases in irregular migration flows, human trafficking, smuggling and other illegal activities. Surveillance technologies can help tackle these issues, but their impact on society in areas such as migration, asylum, and border management needs to be anticipated and addressed from the technology’s infancy.

It is vital that researchers support technology developers and public authorities in their efforts to map, analyse, mitigate and monitor ethical issues that may arise from the use of border management technology. These include, for example, challenges raised by the usage of Satellites, Unmanned Aerial Vehicles (drones), Radar, CCTV, Infrared Cameras, Smart Cameras, etc.

The EU- funded EURMARS project is developing a platform for maritime surveillance to improve the efficiency of border security. Our research in the project showcased how taking an Ethics by Design approach from the first stages of the technology development can ensure that it is developed in an ethical way, placing human rights and civil society protection at the forefront, while boosting its efficiency and applicability to meet our end-users’ needs.

To support project partners in developing the EURMARS platform in alignment with EU guidelines and best practices, we developed an Ethics Risk Assessment Tool. The tool’s main function is to identify potential risks, monitor ethics, and recommend appropriate mitigation measures.

Revolutionizing Maritime Security: EURMARS Project’s Cutting-Edge Coastal Surveillance System

Written by george.armagos on 1 April 2024. Posted in Article.

Article by
SKYLD LTD

In response to the escalating challenges in maritime security within the European Union, the EURMARS project emerges as a groundbreaking initiative aimed at tackling complex threats such as human trafficking, and illegal activities like drug and arms trafficking. One of the components of the product/service to be offered by this visionary project, is the development of the Coastal Ground and Low Altitude Sensing Systems, a critical component in revolutionizing border surveillance, entrusted to SKYLD LTD an innovative Cypriot company.

Unraveling the Complexity of Maritime Security

The maritime domain faces an ever-evolving landscape of threats, necessitating a coordinated and technologically advanced approach. The EURMARS project aims to foster collaboration among national, regional, and EU-level authorities to enhance situational awareness and operational efficiency. The focus is on developing a secure multitasking surveillance platform that integrates high-altitude technology, satellite imagery, Uninhabited Vehicles (UxVs), and ground-based sensors for comprehensive border surveillance.

Skyld Ltd’s Contribution: Coastal Ground and Low Altitude Sensing Systems

This module is designed to generate reliable geo-referenced detections and tracking of ships, small vessels, persons, and vehicles in real-time under challenging maritime conditions. The UAV Platform utilizes airborne camera systems triggered by abnormal events detected by other sensors, verifying and confirming events during patrols.

Technical Specifications Unveiled

The intricate design of the Coastal Ground and Low Altitude Sensing Systems is a testament to Skyld Ltd’s commitment to innovation. The system incorporates:

Camera Sub-Systems: Combining shortwave IR, UV, thermal, and RGB cameras with ROS2 software libraries for live/raw image processing.
Vessel/Vehicle Classification Sub-System: Employs PyTorch for offline training on representative datasets, ensuring real-time classification using GPU technology.
Behaviour Analysis/Anomaly Detection Sub-System: Developed in Python, leveraging MQTT message broker for seamless integration with other components.

Conclusion: A Paradigm Shift in Maritime Security

The EURMARS project, stands at the forefront of a paradigm shift in maritime security. The integration of cutting-edge technologies, AI-based systems, and collaborative frameworks signals a commitment to fortifying the EU’s borders against emerging threats. As the Coastal Ground and Low Altitude Sensing Systems take shape, the consortium moves closer to realizing a future where comprehensive surveillance ensures the safety and security of European waters. The visionary approach of EURMARS, is set to redefine the standards of maritime security in the years to come.

EURMARS – A Multimodal Fusion Architecture for Sensor Applications (MuFASA)

Written by george.armagos on 27 October 2023. Posted in Article.

Article by
AIT Austrian Institute of Technology

The overall vision of the project is to develop a platform that will improve sensing capabilities for wider areas by integrating high altitude technology, satellite imagery and UxVs in addition to ground sensor platforms in order to prevent, detect and react to crime, including that crossing external borders, illegal border crossings and/or smuggling at the border regions of the EU and of the Schengen area. With this challenge a wide arsenal of sensors and external data sources is needed to withstand the complexity of the use-cases. Thus, a sophisticated data fusion approach within a modular architecture is essential.

In EURMARS data fusion has a central role in combing homogeneous and heterogenous data with the goal to improve the overall confidence in detecting use-case specific events. In particular, the data fusion capabilities involve the alignment of the different data delivered by the individual sensors and systems to gain additional information which can not be obtained by individual systems alone. The goal is to decrease false alarms by combining different data sources as well as increase measurement precision to metadata interpretation.

To achieve this goal, different individual data fusion modules are being developed or further improved within EURMARS. Some of them already have shown great promise in previous projects (e.g FOLDOUT), such as the MuFASA (Multimodal Fusion Architecture for Sensor Applications) developed by AIT.

MuFASA addresses various disciplines in terms of Data Fusion on different levels, such as data imperfection, data alignment/registration and data heterogeneity. In this senses MuFASA provides data fusion methodologies and modules dedicated to said tasks. In EURMRAS, the capabilities of MuFASA will be further improved and developed and are focusing on feature level data fusion. On feature level, MuFASA incorporates a multimodal data fusion methodology based on inference (Bayesian). Beside establishing spatio-temporal coincidence of sensor observations an increased confidence and robustness of a sensing system is achieved.

It´s main advantaged are summarized in a reduction of the overall alarm rates as well as geo-localized fused events. MuFASA therefore benefits in:

Time saving when verifying alarms
Same sensor technology as competitors, better detection rates and fewer false alarms.
Trust in overall sensor system is strengthened
No installation effort

By providing a real-time data fusion approach, sensor observation immediately can be fused to establish situational awareness in the use-cases defined within the EURMARS project. One challenge in the given setting is, that not only real-time data is available, but also semi-real time data (such as satellite images) and external data sources such as AIS[1]. This puts MuFASA before a new set of challenges, which will be evaluated within the project scope.

Due to its core methodology (inference), MuFASA excels in reducing the overall false alarms produced by single sensor systems. This is considered as one of the main impacts of the EURMARS system.

[1] AIS – Automatic identification system – Transponders are designed to be capable of providing position, identification, and other information about the ship to other ships and to coastal authorities automatically.