Enhancing the Security, Privacy and Robustness of AI Models and Systems (SecureAI)
Open
Status as published by the data source.
Expected Outcome:
Proposals are expected to contribute to one or more of the following:
• Robust AI models and systems capable of resisting different classes of adversarial manipulation;
• Innovative defence mechanisms for AI models and systems against new attack families;
• Methodologies for detecting and mitigating attacks, such as data poisoning, backdoor exploitation and misclassification;
• AI systems leveraging privacy-enhancing technologies that maintain data confidentiality and regulatory compliance, enabling trusted in-house AI deployments (e.g., for governments and enterprises). Scope:
The increasing reliance on AI in cybersecurity, critical infrastructure, and decision-making processes raises concerns about the security and robustness of AI systems. As AI systems become more prevalent, they are increasingly targeted by adversarial attacks that manipulate inputs, compromise training data, or introduce hidden vulnerabilities. This topic aims to strengthen the resilience of AI systems and algorithms against various threats and attacks, such as enhancing their resilience against adversarial attacks, backdoor injections, and data poisoning. Proposals should develop real-time anomaly detection, mitigation techniques to defend against adversarial attacks and robust federated learning techniques, in synergies with leading efforts on AI transparency, and in compliance with the AI Act. The topic is expected to:
• Develop robust AI models resistant to adversarial attacks. Exploring techniques to harden AI models and systems against adversarial perturbations, such as adversarial training, robust optimisation, and defence mechanisms that enhance the trustworthiness of AI.
• Improve detection of manipulated or poisoned training data. Advancing methodologies to identify and mitigate compromised datasets, leveraging techniques such as anomaly detection, provenance tracking, and automated data validation mechanisms.
• Address the concept of Private AI by developing mechanisms that enable AI models to be trained, deployed and operated in privacy-preserving environments, particularly for sensitive use cases, as for example for government and enterprise settings. This includes ensuring AI computations and data remain within trusted execution boundaries (e.g. on-premise or regulated cloud environments), and leveraging existing and emerging privacy-enhancing techniques such as federated learning, secure aggregation, computing on encrypted data, quantum-safe homomorphic encryption and secure inference in deep learning to safeguard the protection of personal and other sensitive data throughout the AI lifecycle.
- Status
- Open
- Deadline
- (time not stated)
- Opens
- Published
- Total budget
- €21,200,000
- Grant range
- €3,000,000 – €4,000,000
- Country
- European Union (EU-wide)
- Programme
- Horizon Europe (HORIZON)
- Official page
- Open at the source portal
Other calls under Horizon Europe (HORIZON)
- PV based electrification of the economy: Designing & optimising PV systems supporting industrial electrification and promoting participation in electricity markets (EUPI-PV Partnership)
- Advanced TSO control rooms to enhance grid observability, stability and resilience
- Advanced Distribution Management Systems (ADSM) for more efficient and flexible distribution grids
- Community of practice - Data-Driven Decision-Making in Energy
- Industrial processes and equipment for innovative, reliable and scalable tandem technologies (EUPI-PV Partnership)
- Integrated Approaches for Retrofitting Infrastructures with Innovative Energy Storage Technologies
- Demonstration of hydropower technologies for efficient and forward-looking refurbishment of existing hydropower plants
- Delivery of industrial CCUS clusters – Societal Readiness pilot
All calls under this programme
Similar opportunities
- Artificial Intelligence for Cybersecurity applications
- Data sharing to support the training and development of AI foundation models in the energy sector
- Secure Computing Continuum (IoT, Edge, Cloud, Data spaces)
- Addressing the impact of artificial intelligence, cyberviolence, and deepfakes on equality, democracy and inclusive societies
- Energy efficiency and sustainability of AI data processing in Data Centres (IA)
- Security of robust AI systems
Where this came from
- Source document
- https://ec.europa.eu/info/funding-tenders/opportunities/data/topicDetails/horizon-cl3-2026-02-cs-eccc-02.json
- Document fingerprint
ee9cf76037b3c99f(SHA-256, first 16 hex characters)- Retrieved
- First recorded here
What has changed
- url first recorded as https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/opportunities/topic-details/horizon-cl3-2026-02-cs-eccc-02 on
- currency first recorded as EUR on
- amount_max first recorded as 4000000.00 on
- amount_min first recorded as 3000000.00 on
- budget_total first recorded as 21200000.00 on
- deadline first recorded as 2026-09-15 on
- opens_on first recorded as 2026-03-03 on
- published_on first recorded as 2025-12-12 on
- status_basis first recorded as source_status on
- status first recorded as open on
- title first recorded as Enhancing the Security, Privacy and Robustness of AI Models and Systems (SecureAI) on
Data source
© European Union, 2026. Source: EU Funding & Tenders Portal. Reused under Commission Decision 2011/833/EU — CC BY 4.0.
Retrieved from the source on .
The source last updated this document on Mon, 09 Mar 2026 15:29:01 GMT.
Personal data of natural persons has been dissociated by quiescence.eu.
This service is not affiliated with, sponsored or endorsed by the data publishers.