Skip to main content
All Posts By

Anna Marton, Safepay Systems

When AI Can Be Fooled – Robust Models as the Goal of Modern AI Projects Insights

When AI Can Be Fooled – Robust Models as the Goal of Modern AI Projects

By Marvin Vogt, Fraunhofer FOKUS Whether it’s self-driving cars, malware detection, or text generation: neural networks have long since established themselves as a key technology for many innovative applications. However, it has become apparent that such machine learning systems are vulnerable to malicious actors. This article is intended to provide a…
ASSIST Software Promotes SECASSURED at FSAS Technologies Summit 2026 News

ASSIST Software Promotes SECASSURED at FSAS Technologies Summit 2026

Our project partner ASSIST Software represented SECASSURED at the FSAS Technologies Summit 2026, on 1-2. July 2026 in Munich, Germany, showcasing the project's vision and innovative approach to strengthening cybersecurity for connected systems. Events like the FSAS Technologies Summit provide valuable opportunities to engage with industry experts, exchange ideas on…
Digital Twins-based Assurance-driven AI-empowered SecDevOps Insights

Digital Twins-based Assurance-driven AI-empowered SecDevOps

By Phu Nguyen and Adela Nedisan Videsjorden, SINTEF Digital systems today are more complex and critical than ever. They are built from many interconnected components, often combining third-party hardware and software. At the same time, rapid development cycles and evolving cyber threats—especially with Generative AI—make security increasingly difficult. SECASSURED envisions Digital…
Project Partners Gather in Oslo for the Second General Assembly Meeting News

Project Partners Gather in Oslo for the Second General Assembly Meeting

The SECASSURED consortium met in Oslo, Norway on 10-11. June 2026, for its second General Assembly, hosted by SINTEF. Bringing together project partners from across Europe, the two-day meeting provided an important opportunity to review the project's progress, discuss achievements, and align on the next steps towards delivering SECASSURED's objectives.…
Voulkopoulou A, Kalouptsoglou I, Kehagias D, Tzovaras D. 2026. Context Matters: Vulnerability Categorization with Dual-Input Code Representations. LIFESEC 2026. Publications

Voulkopoulou A, Kalouptsoglou I, Kehagias D, Tzovaras D. 2026. Context Matters: Vulnerability Categorization with Dual-Input Code Representations. LIFESEC 2026.

Conference: 2nd Workshop on Whole-Lifecycle Security for Smart Systems: Methods and Tools (LIFESEC 2026), collocated with the 12th IEEE International Conference on Smart Computing (SmartComp 2026) 22. June 2026, Messina, Italy Authors: Voulkopoulou A, Kalouptsoglou I, Kehagias D, Tzovaras D. Abstract: Nowadays, software security is considered an important aspect of…
Savvy Data Systems and IDEKO Research Center Promote SECASSURED at Advanced Factories 2026 News

Savvy Data Systems and IDEKO Research Center Promote SECASSURED at Advanced Factories 2026

Our project partners Savvy Data Systems and IDEKO Research Center represented SECASSURED at Advanced Factories 2026 in Barcelona, showcasing the project's vision for strengthening cybersecurity in smart manufacturing and connected industrial environments. As one of Europe's leading events for industrial innovation, automation, robotics, and Industry 4.0, Advanced Factories brings together…
ASSIST Software Promotes SECASSURED and Engages Industry at Hannover Messe 2026 News

ASSIST Software Promotes SECASSURED and Engages Industry at Hannover Messe 2026

Our project partner ASSIST Software represented SECASSURED at Hannover Messe 2026, one of the world's leading trade fairs for industrial technology and digital transformation, promoting the project's vision for strengthening cybersecurity in connected and industrial digital environments. Hannover Messe brings together manufacturers, technology providers, researchers, policymakers, and innovators from around…
Siavvas M, Kalouptsoglou I, Kehagias D, Tzovaras D. 2026. Cross-Domain Vulnerability Detection using LLMs: Knowledge Transfer from Contemporary Software to AI/ML-Specific Software. IJCNN 2026. Publications

Siavvas M, Kalouptsoglou I, Kehagias D, Tzovaras D. 2026. Cross-Domain Vulnerability Detection using LLMs: Knowledge Transfer from Contemporary Software to AI/ML-Specific Software. IJCNN 2026.

Conference: International Joint Conference on Neural Networks (IJCNN) 21-26. June 2026, Maastricht, Netherlands Authors: Siavvas M, Kalouptsoglou I, Kehagias D, Tzovaras D. Abstract: The increasing integration of artificial intelligence (AI), and particularly machine learning (ML), into software intensive systems raises security concerns for AI/ML-specific code. Although AI-based vulnerability detection models…