Project description
Securing the future of generative AI
As generative AI becomes embedded in everything, cybersecurity risks are growing fast. Large language models (LLMs) can be manipulated, leak data, or fail under attack, exposing users and companies to serious threats. The EIC-funded NeuralTrust project aims to develop a cybersecurity platform designed specifically for generative AI. It combines three layers of protection: a secure AI gateway to block real-time attacks, AI red teaming to detect vulnerabilities through simulated assaults, and observability tools to monitor AI behaviour and ensure traceability. Unlike existing solutions, NeuralTrust secures all AI traffic at the infrastructure level, protecting entire systems. The project’s overarching goal is for this new technology to become the standard for safe and transparent AI deployment.
Objective
NeuralTrust is a pioneering company in cybersecurity for Generative AI, addressing the multifaceted risks associated with this rapidly evolving technology. Our mission is to ensure the safe, reliable, and measurable deployment of Generative AI, protecting system integrity and user trust. Our vision is to lead the cybersecurity landscape in the Generative AI era by providing robust security measures, real-time monitoring, and regulatory compliance to safeguard against misuse and vulnerabilities. The company tackles significant challenges posed by Large Language Models (LLMs), such as security vulnerabilities, functional failures, privacy breaches, responsibility failures, and availability attacks. NeuralTrust's innovative solution is a holistic cybersecurity platform with three interconnected modules: Secure AI Gateway for real-time attack blocking and service scaling, Algorithmic Red Teaming for targeted attacks to identify vulnerabilities, and Observability for real-time AI behavior analysis and full traceability. This ensures NeuralTrust can address the full spectrum of risks associated with Generative AI. The value proposition lies in its ability to provide comprehensive security for multi-turn conversations, multi-modal interactions, and contextual security, outperforming market alternatives in public benchmarks. Unlike competing guardrail solutions that analyze prompts in isolation and are embedded within individual applications, NeuralTrust is the first to secure all LLM traffic at the infrastructure level while analyzing contextual user behavior – enabled by its pioneering LLM gateway architecture. NeuralTrust's platform covers pentesting, blocking, detection, monitoring, analytics, and compliance, setting it apart from competitors focusing on narrower security aspects. The Generative AI cybersecurity market is projected to grow significantly, and NeuralTrust is well-positioned to address this critical gap with its comprehensive security solution.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
You need to log in or register to use this function
Keywords
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Project’s keywords as indicated by the project coordinator. Not to be confused with the EuroSciVoc taxonomy (Fields of science)
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
-
HORIZON.3.1 - The European Innovation Council (EIC)
MAIN PROGRAMME
See all projects funded under this programme
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
HORIZON-EIC-ACC - HORIZON EIC Accelerator
See all projects funded under this funding scheme
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
(opens in new window) HORIZON-EIC-2025-ACCELERATOR-02
See all projects funded under this callCoordinator
Net EU financial contribution. The sum of money that the participant receives, deducted by the EU contribution to its linked third party. It considers the distribution of the EU financial contribution between direct beneficiaries of the project and other types of participants, like third-party participants.
08018 Barcelona
Spain
The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.