Jul

2

Call for Participation: SafeComp 2026

July 2, 2026 | | Comments Off on Call for Participation: SafeComp 2026

We are pleased to invite you to participate in the 45th International Conference on Computer Safety, Reliability, and Security (SafeComp  2026), which will be held in Valencia, Spain, from September 22-25, 2026.

We highly encourage you to take advantage of our Early Bird registration rates, which expire on July 14, 2026. Register now at https://safecomp2026.webs.upv.es/registration to secure your spot and explore everything SafeComp 2026 has to offer:

  • Dive deep into specific industrial challenges and enjoy excellent networking opportunities during our Workshop Day (September 22, 2026), featuring emerging topics in the field:
    • 1st Int. Workshop on Cybersecure Supply Chains for Safe and Resilient Industrial Systems (CSRIS).
    • 13th Int. Workshop on Next Generation of System Assurance Approaches for Critical Systems (SASSUR).
    • 21st Int. Workshop on Dependable Smart Embedded Cyber-Physical Systems and Systems-of-Systems (DECSoS).
    • 1st Int. Workshop on OverReliance on Cognitive AI Systems in Safety-Critical Domains (ORCAS).
    • 2nd Int. Workshop on Disruptive Safety Challenges and Paradigms (SafetyNXT).
    • 1st Int. Workshop on Dependable AI in Embedded Systems (DAIES).
    • 5th Int. Workshop on SafEty aNd SEcurity Interactions (SENSEI).
    • 9th Int. Workshop on Artificial Intelligence Safety Engineering (WAISE).
  • Attend exciting sessions in the main program (September 23-25, 2026) covering the cutting edge of safety-critical systems, autonomous driving, AI safety, cybersecurity, and formal methods.
  • Hear from industry leaders and academic pioneers who are shaping the future of dependable systems:
    • Toward Large-Scale Fault-Tolerant Quantum Computers: Security in the Quantum Era – Carmen G. Almudéver, Department of Computer Engineering, Universitat Politècnica de València (Spain).
    • Physical AI Safety: A Unified Framework for Safety, Security, and AI Assurance – Gianpiero Negri, Robotics Safety Center of Excellence, Amazon Robotics (Italy).
    • Combining High-Performance Hardware and Software with High Software Assurance: Is it Possible? – Leonidas Kosmidis, Barcelona Supercomputing Center (Spain).
  • Connect with international experts, researchers, and leading companies against the beautiful backdrop of Valencia during our social and networking events.

The full conference scientific and social programs are available at https://safecomp2026.webs.upv.es/program-final and https://safecomp2026.webs.upv.es/social-programme, respectively.

Don’t miss the chance to save on your registration fee and join the definitive event for computer safety and reliability in Europe.

We look forward to welcoming you to Valencia!

Jul

1

Paper Accepted at DAIES 2026: A Framework for the Automatic Deployment of Dependability Mechanisms on PyTorch-Based Models

July 1, 2026 | | Comments Off on Paper Accepted at DAIES 2026: A Framework for the Automatic Deployment of Dependability Mechanisms on PyTorch-Based Models

We are pleased to announce that our paper “A Framework for the Automatic Deployment of Dependability Mechanisms on PyTorch-Based Models” has been accepted for presentation at the 1st International Workshop on Dependable AI in Embedded Systems (DAIES 2026).

As Artificial Intelligence becomes increasingly integrated into safety- and mission-critical systems, ensuring the dependability of AI models has become a fundamental challenge. While numerous fault-tolerance techniques have been proposed, integrating them into existing neural networks often requires significant manual effort and expert knowledge.

In this paper, we present a framework that automates the deployment of dependability mechanisms in PyTorch-based neural networks. The proposed solution enables AI models to be enhanced with reliability features while minimizing developer intervention, facilitating the adoption of dependable AI practices throughout the development process.

The framework has been designed to support the systematic evaluation and integration of dependability mechanisms, helping researchers and practitioners improve the robustness of AI systems without modifying the original application logic. By reducing the complexity of incorporating fault-tolerance techniques, it contributes to accelerating the development of trustworthy AI solutions for safety-critical embedded systems.

We are proud to contribute to DAIES 2026, a forum dedicated to advancing the reliability, safety, security, and certification of intelligent embedded and autonomous systems.

We look forward to presenting our work and discussing future directions in dependable AI with the DAIES community.

More info at: https://safecomp2026.webs.upv.es/daies-2026

Jun

30

Conference Program for SafeComp 2026 Now Available

June 30, 2026 | | Comments Off on Conference Program for SafeComp 2026 Now Available

We are pleased to announce that the final program for SafeComp 2026 is now available!

This year’s conference offers an exciting agenda covering the latest advances in computer safety, reliability, security, and dependable AI, bringing together researchers and practitioners from academia and industry. The program features inspiring keynote talks, technical sessions, workshops, social events, and numerous opportunities for networking and scientific discussion.

Among the highlights of the conference are:

Three keynote presentations by internationally recognized experts.
Technical sessions covering topics such as AI assurance, fault tolerance, safety engineering, cybersecurity, formal methods, and dependable embedded systems.
A full day of specialized workshops, including DAIES and other satellite events.
Social activities designed to foster collaboration within the SafeComp community.

Whether you are interested in dependable AI, safety-critical systems, autonomous technologies, or cybersecurity, SafeComp 2026 offers a unique single-track program that allows participants to attend every presentation without parallel sessions, maximizing opportunities for interaction and knowledge exchange.

Take a look at the complete program and start planning your visit to Valencia!

Conference Program: https://safecomp2026.webs.upv.es/program-final/

We look forward to welcoming you to Valencia from 22–25 September 2026 for another outstanding edition of SafeComp.

Jun

30

Keynote Announcement: Neuromorphic AI for Safety-Critical Embedded Systems at DAIES 2026

June 30, 2026 | | Comments Off on Keynote Announcement: Neuromorphic AI for Safety-Critical Embedded Systems at DAIES 2026

We are delighted to announce the keynote speaker for the 1st Int. Workshop on Dependable AI in Embedded Systems (DAIES 2026).

Daniel Gutiérrez, CEO and founder of Intigia, will deliver the keynote entitled:

From Silicon to Outer Space: Deploying Neuromorphic AI and SWaP Optimization in Critical Embedded Environments

Artificial Intelligence is rapidly moving from cloud infrastructures to embedded platforms operating in safety- and mission-critical environments. However, deploying AI in domains such as aerospace, autonomous vehicles, industrial automation, and robotics requires overcoming major challenges related to power consumption, predictable execution, functional safety, and certification.

In this keynote, Daniel Gutiérrez will explore how neuromorphic computing, Edge AI, and hardware/software co-design are helping address these challenges. Drawing on Intigia’s experience in European and industrial R&D projects, the presentation will discuss innovative approaches to designing intelligent embedded systems that meet strict Size, Weight, Power, and Cost (SWaP) constraints while delivering the performance and reliability required by critical applications.

With more than twenty years of experience in embedded electronics, semiconductor design, FPGA architectures, and functional safety, Daniel currently leads several pioneering initiatives in neuromorphic hardware and sustainable AI, including the AceleradorSNN and NeuroAI4Space projects.

This keynote promises to provide valuable insights into the future of dependable Edge AI, showcasing how bio-inspired computing and specialized hardware are paving the way for the next generation of intelligent systems in aerospace, automotive, and industrial applications.

We look forward to welcoming Daniel Gutiérrez to DAIES 2026 and to an inspiring discussion on the future of neuromorphic AI in safety- and mission-critical systems.

More info at: https://safecomp2026.webs.upv.es/daies-2026/

Jun

30

Paper Accepted at DAIES 2026

June 30, 2026 | | Comments Off on Paper Accepted at DAIES 2026

The paper entitled “Dependability Analysis of a Spiking Convolutional Neural Network (S-CNN)”, written by Joaquín Gracia-Morán, J. Carlos Baraza-Calvo, Juan-Carlos Ruiz, David de Andrés, Daniel Gil-Tomás, and Luis-J. Saiz-Adalid, has been accepted in the 1st Int. Workshop on Dependable AI in Embedded Systems (DAIES 2026).

The paper investigates the reliability of Spiking Convolutional Neural Networks (S-CNNs) when exposed to memory faults, an increasingly important topic as neuromorphic computing gains traction in safety- and mission-critical embedded applications. Through an extensive software-implemented fault injection campaign, we evaluate the effects of adjacent multi-bit memory faults on both convolutional and spiking neuron layers.

Our results show that the proposed S-CNN exhibits a high degree of intrinsic robustness, maintaining correct classifications in most fault scenarios. The study also identifies the LIF neuron parameters as the most critical components from a dependability perspective, providing valuable insights for the design of future fault-tolerant neuromorphic systems.

Jun

16

DAIES 2026 Program Now Available

June 16, 2026 | | Comments Off on DAIES 2026 Program Now Available

We are pleased to announce that the technical program for the first edition of the Workshop on Dependable AI in Embedded Systems (DAIES 2026) is now available.

DAIES 2026 will take place on 22 September 2026 in Valencia, Spain, as a co-located workshop of the 45th edition of SafeComp, the International Conference on Computer Safety, Reliability and Security.

The workshop will bring together researchers and practitioners working on the design, verification, validation, and certification of AI-enabled embedded and cyber-physical systems, with a particular focus on dependability attributes such as safety, reliability, availability, and security.

The program features presentations covering a broad range of topics, including:

  • AI safety engineering for automotive and industrial domains
  • Dependability assessment of neural networks and spiking neural networks
  • Fault injection and radiation effects in AI-enabled systems
  • Runtime monitoring and resilient AI architectures
  • Safety assurance of large language models in critical applications

In addition to the technical sessions, the workshop will include an invited keynote presentation by a distinguished expert in the field. The keynote speaker will be announced soon.

DAIES 2026 is part of the SafeComp workshop day, which will be held on 22 September 2026, ahead of the main conference taking place from 23 to 25 September 2026 in Valencia.

We invite all researchers, engineers, and practitioners interested in dependable AI for embedded and safety-critical systems to explore the program and join us in Valencia.

More information, including the complete workshop program, is available at: https://safecomp2026.webs.upv.es/daies-2026/

May

28

Explore the SafeComp 2026 Workshops

May 28, 2026 | | Comments Off on Explore the SafeComp 2026 Workshops

SafeComp 2026 is not only a leading conference on computer safety, reliability, and security, but also an excellent opportunity to engage with specialized communities through its exciting workshop program.

The workshops associated with SafeComp 2026 provide focused forums where researchers, practitioners, and industry experts can discuss emerging challenges, innovative methodologies, and future trends in dependable and trustworthy systems. They offer a more interactive environment than the main conference, encouraging in-depth discussions, networking, and collaboration.

This year’s workshops cover a wide range of topics related to safety-critical and intelligent systems, including dependable AI, cybersecurity, embedded systems, fault tolerance, verification and validation, autonomous systems, and sustainable computing technologies.

Whether you are a researcher presenting early-stage ideas, an engineer looking for practical solutions, or a student exploring new research directions, the SafeComp workshops are an excellent place to exchange ideas and connect with the community.

We warmly invite all conference participants to explore the workshop program and join the discussions shaping the future of dependable computing systems.

📅 SafeComp 2026 will take place in Valencia, Spain, from September 22–25, 2026.

🔗 More information about the workshops and conference program can be found on the official website:
https://safecomp2026.webs.upv.es/

May

28

New publication in ACM Transactions on Reconfigurable Technology and Systems

May 28, 2026 | | Comments Off on New publication in ACM Transactions on Reconfigurable Technology and Systems

We are pleased to share our latest research article:

“An Open Source Methodology to Emulate Transient Faults in ASIC Storage Cells Using AMD Ultrascale+ FPGAs”

Authors: Ilya Tuzov, David de Andrés, Juan-Carlos Ruiz and Carles Hernández.

The paper presents an open-source methodology for emulating transient faults in ASIC storage cells using AMD Ultrascale+ FPGAs. The work extends FPGA fault injection capabilities beyond configuration memory bit-flips, enabling the emulation of transient faults in sequential logic cells and on-chip memories, which are critical for dependable ASIC prototyping and validation.

The proposed methodology is integrated into the publicly available BAFFI tool and validated through experimental campaigns on MC8051 and NOEL-V soft-core processors.

📄 Read the paper:
https://doi.org/10.1145/3797884

#FPGA #ASIC #FaultInjection #Dependability #HardwareDesign #OpenSource #EmbeddedSystems #Reliability

May

27

Registration for SafeComp 2026 is now open!

May 27, 2026 | | Comments Off on Registration for SafeComp 2026 is now open!

Join the 45th International Conference on Computer Safety, Reliability and Security, taking place in Valencia, Spain, from September 22–25, 2026.

SafeComp 2026 will bring together researchers, industry professionals, and practitioners working on safety, reliability, cybersecurity, AI, and dependable critical systems under the theme:

🔹 Engineering safe and sustainable computing systems 🔹

The conference will feature:
✅ Research and industrial sessions
✅ Workshops and position papers
✅ A unique single-track format encouraging networking and discussion
✅ The opportunity to connect with the international dependable systems community

📍 Valencia, Spain
📅 September 22–25, 2026

Registration is available here:
SafeComp 2026 Registration

More information about the conference:
SafeComp 2026 Website

Mar

24

Call for Papers: DAIES Workshop @ SafeComp 2026

March 24, 2026 | | Comments Off on Call for Papers: DAIES Workshop @ SafeComp 2026

We are pleased to announce the Call for Papers for the DAIES Workshop 2026, co-located with SafeComp 2026, to be held in Valencia, Spain, with Joaquín Gracia acting as Workshop Organizer.

About the workshop

This workshop will provide a focused forum on how to design, verify, and certify AI-enabled embedded systems while preserving their overall dependability, including safety, reliability, availability, and security, under tight resource and real-time constraints. It targets AI-enabled embedded and cyber-physical systems deployed in safety-critical domains such as automotive, rail, aerospace, robotics, medical devices, and industrial control. The workshop will emphasize how functional safety, cybersecurity, and sustainability jointly contribute to system dependability when AI models, often opaque and non-deterministic, are deployed on constrained embedded platforms exposed to both accidental faults and malicious attacks.

Call for Papers

Researchers and practitioners are invited to submit original contributions presenting novel ideas, work-in-progress, or practical experiences related to the workshop topics. Workshops at SafeComp offer a collaborative environment to exchange ideas and discuss emerging challenges in safety, reliability, and sustainability of critical systems.

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

  • Safe architectures and engineering approaches: Design and standards-compliant deployment of AI in embedded and cyber-physical systems.
  • Verification, validation, and resilience: Testing, robustness, and fault-tolerance methods for reliable AI in constrained environments.
  • Security, monitoring, and lifecycle management: Safety-security co-engineering, runtime monitoring, and continuous assurance of AI systems.
  • Applications, tools, and evidence: Real-world case studies and resources for evaluating trustworthy AI in embedded systems.

Accepted full workshop research papers will be included in the complementary book of the SafeComp 2026 Proceedings. Templates for paper preparation can be downloaded from: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines.

Important Dates

  • Paper submission: 4 May 2026.
  • Notification of acceptance: 18 May 2026.
  • Camera-ready papers: 8 June 2026.
  • Workshop date: 22 September 2026 (co-located with SafeComp 2026).

Join Us

DAIES 2026 aims to bring together researchers, industry experts, and practitioners to advance the state of the art in safe and reliable AI-enabled systems. We encourage you to contribute and be part of this exciting discussion.

We look forward to your submissions!

More information: https://safecomp2026.webs.upv.es/daies-2026/