PLURIBUS ONE

Profile & expertise

PLURIBUS ONE, founded in 2015 and born as a spin-out of the Pattern Recognition and Applications (PRA) Lab at Univ. Cagliari, is a research-intensive company, focused on providing innovative solutions and services for cyber security. It is in fact a vendor of trustworthy AI/ML solutions for cyber security.

Our leading product” Seerbox” is an AI/ML-based Web Application Security Manager with Active installations among Regional Governments, e-commerce, Banks, Transport, Education.

Additionally, we recently certified with the ISO 27001 Certified software development process.

The company has also a very strong track record of EU/national research projects

Relevant Projects:

1. STARLIGHT – https://starlight-h2020.eu – The project focuses on increasing the awareness, capability, adoption, and long-term impact of AI in Europe for LEAs. Law enforcement agencies’ (LEAs) data-rich environments provide the opportunity to adopt AI tools and capabilities that improve investigatory practices and limit the criminal misuse of AI. Through STARLIGHT, LEAs will collaboratively develop their autonomy and resilience in the use of AI for tackling major criminal threats.
2. ELSA –  The goal of the project is to establish a new pillar for the European AI lighthouse on safe and secure AI. In order to reinforce European leadership in safe and secure AI technology, The project is proposing a virtual center of excellence on safe and secure AI that is geared towards addressing the major challenges hampering the deployment of AI technology. The grand challenges are of fundamental nature and therefore can only be addressed in a sustainable manner by a lighthouse that is built on top of scientific excellence and rigorous methodology. With a focus on technical robustness and safety, privacy preserving techniques and infrastructures as well as human agency and oversight, Elsa is shaping the future of safe and secure AI toward trustworthiness.
3. SIMARGL – Secure Intelligent Methods for Advanced Recognition of Malware and Stegomalware. The SIMARGL project is about the development of an intelligent platform for the detection of malware and stegomalware. Pluribus One participates to the project being responsible for the exploitation work-package, and contributing from a technical standpoint with its expertise on adversarial machine learning and integrating its solution into the SIMARGL platform.
4. AIDA – Artificial Intelligence and Advanced Data Analytics for Law Enforcement agencies. The AIDA project aims to deliver a descriptive and predictive data analytics platform and related tools using state-of- the-art machine learning and artificial intelligence methods to prevent, detect, analyze, and combat criminal activities. AIDA focus on cybercrime and terrorism, by addressing specific challenges related to law enforcement investigation and intelligence.
5. AssureMOSS – Assurance and certification in secure Multi-party Open Software and Services. AssureMOSS proposes to switch from process-based to an artefact-based security evaluation by supporting all phases of the continuous software lifecycle (Design, Develop, Deploy, Evaluate and back) their artefacts (Models, Source code, Container images, Services). The key idea is to support mechanisms for lightweigth and scalable screenings applicable automatically to the entire population of software components by
   • Machine intelligent identification of security issues across artifacts,
   • Sound analysis and verification of changes by tracing the security and privay side effects,
   • Business insight by risk analysis and security evaluation.

   PLURIBUS ONE contributes with its background on secure and explainable machine learning, contributing to the development of a machine learning component for lightweight code analysis in order to search vulnerability in the source code. PLURIBUS ONE is also responsible for defining the tool flow evaluation plan and a comprehensive risk management strategy. In addition PLURIBUS ONE is involved into the Dissemination and Communication activities and contributes the communication activity with the EC officers.

6. TESTABLE – Testability-driven Security And pRivacy testing for Web Applications. TESTABLE addresses the grand challenge of building and maintaining modern web-based and AI-powered application software secure and privacy-friendly. TESTABLE intends to lay the foundations for a new integration of security and privacy into the software development lifecycle (SDLC), by proposing a novel combination of two metrics to quantify the security and privacy risks of a program, i.e., the code testability and vulnerable behavior indicators. Based on the novel concept of “testability patterns”, TESTABLE empowers the SDLC actors (e.g., software/AI developers, managers, testers, and auditors) to reduce the risk by building better security and privacy testing techniques for classical and AI-powered web applications, and removing or mitigating the impact of the patterns causing the high-risk levels. In this project PLURIBUS ONE coordinates the definition of AI/ML testing scenarios for AI/ML developers, and their implementation and integration with existing software development lifecycles. PLURIBUS ONE also works on the definition and identification of the corresponding testability patterns, related to the use of AI/ML models within web applications. In addition, PLURIBUS ONE contributes to the validation of the AI/ML testing tools developed. PLURIBUS ONE is also involved in technology transfer and integration of TESTABLE’s prototypes and AI/ML testing into its products. It also contributes to the scientific dissemination of the project results in the area of AI/ML security and privacy.”

Role in the Project

In addition to developing the use case in the financial sector with Numera, Pluribus One has the leadership of WP7 on Dissemination, Communication & Exploitation, which has the goals of raising awareness for the research carried out within the project and promoting the scientific knowledge generated during it.