Welcome to Saifer lab
Joint Lab on Safety and Security of AI
The sAIfer Lab is a virtual lab founded in 2024 to strengthen and expand the activities of the two founding partners, the PRA Lab and the SmartLab, in the strategic areas of AI and Cybersecurity and create added value for all the partners and stakeholders of the Universities of Cagliari and Genoa. sAIfer Lab research fits in the so called Pasteur’s quadrant, conjugating the search for fundamental understanding of scientific problems with practical use for society in fields of cybersecurity, biometrics, and industry. The Lab has a special focus on the development of safe and secure AI systems that ensure that no unintentional or intentional harm can occur to people, IT systems, society, and critical infrastructures. Unintentional harms due to the lack of safety of AI systems to unexpected situations. Intentional harms due to the lack of security of AI systems against attacks.
2 Joint Research Laboratories
The official website of thePRASMARTsAIferLab.
The Joint Lab on Safety and Security of AI.


Nielse Bohr's quadrant
Pure Basic Research

Louis Pasteur's quadrant
Use-inspired Basic Research

Thomas Edison's quadrant
Applied Research
sAIfer Lab Pasteur’s Research Quadrant
Louis Pasteur research paradigm: research questions that arise from practical considerations of use and require a novel and fundamental understanding.
sAIfer Lab's research aligns with Pasteur’s quadrant, merging the pursuit of fundamental scientific understanding with practical applications in cybersecurity, biometrics, and industry, thereby working to protect people, IT systems, society, and critical infrastructures.
TESTIMONIALS - INDUSTRIAL PARTNERS
TESTIMONIALS - FORMER RESEARCHERS
ENDORSEMENTS
OUR SERVICES
The thirty-year experience of the sAIfer Lab researchers guarantees a wide training offering of courses and seminars, consultancy, technology transfer and solid collaboration in proposing and conducting research and development projects.
Technology Transfer
sAifer Lab promotes collaboration between university research and businesses with the aim of transferring frontier innovation to companies and startups, and giving to its industrial partners a competitive advantage on the market.
EU projects partnership & Leadership
sAIfer Lab researchers have a great experience in leading R&D projects funded under the European Research Framework Programmes. sAIfer Lab is constantly looking for new partners to develop innovative and stimulating projects.
MLSec Courses and seminars
sAIfer Lab organizes "MLSec Seminars". With more than 25 episodes aired since it’s started in 2022, this series of free online seminars has become a venue for discussing new developments in the field of Machine Learning Security.
Consulting on Security and Safety of AI systems
sAIfer Lab researchers make available their experience in the fields of AI Security & Safety, Trustworthy AI, AI Explainability, Biometrics, Cybersecurity, to offer consultancy to public and private institutions at a local, national and international level.
Ask for a Service
Get immediate feedback on our offer and on your collaboration proposal.
HIGHLIGHTS
PROJECTS
The goal of the InfoAICert project is to develop the first made-in-Italy platform for conformity assessment of high-risk AI systems. This goal will be reached by leveraging on the world-class research leadership of P.I. Fabio Roli on AI security and trustworthy AI and on the international leadership of the company Tinexta/InfoCert as trust service provider.
RESEARCH
Tutorial "Towards Adversarially Robust ML in The Age of The AI Act " accepted at the prestigious ECAI-2025. Presenters: Lorenzo Cazzaro and Antonio Emanuele Cinà.
The tutorial will explore security threats targeting AI, including adversarial examples that induce misclassification or indecision, data poisoning attacks, and jailbreak techniques.
RESEARCHERS
Battista Biggio has been elevated to IEEE Fellow, for his "contributions to the security of machine learning".
IEEE Fellow is a distinction reserved for selected IEEE members with extraordinary accomplishments. Each year, following a rigorous evaluation procedure, less than 0.1% of IEEE members are selected by the IEEE Fellow Committee, for this member grade elevation.
TECHNOLOGY TRANSFER PARTNERS












