CSP–IAS Winter School on Cryptography and Machine Learning.
Where: Turin, OGR
When: 2–5 February 2026
The CSP–IAS Winter School on Cryptography and Machine Learning will take place in Turin from 2 to 5 February 2026, at the OGR.
The Winter School marks the conclusion of the first year of the CSP–IAS – the Institute for Advanced Study of AI4I, established with the contribution of Fondazione Compagnia di San Paolo. Designed as a flagship event, it aims to bring together an international audience to explore one of today’s most advanced frontiers: the intersection of cryptography and machine learning.
The School is organized under the scientific direction of:
- Valerio Cini, Postdoctoral Researcher, Bocconi University
- Giulio Malavolta, Assistant Professor, Bocconi University
- Tamer Mour, Postdoctoral Researcher, Bocconi University
- Emmanuela Orsini, Assistant Professor, Bocconi University
- Alon Rosen, Full Professor of Computer Science, Bocconi University
Among the invited speakers are some of the world’s leading computer scientists, including Shafi Goldwasser and Adi Shamir, both Turing Award laureates, as well as other distinguished researchers whose lectures will ensure a high-level and inspiring program.
Assumed Background of Participants
The School is primarily intended for graduate students (Master’s and PhD), postdoctoral researchers, and early-career academics, though we also welcome participants from industry or those with a general interest in this area.
Participants should have a solid background in undergraduate-level mathematics (linear algebra, probability, discrete mathematics). Prior experience in both cryptography and machine learning is not required, but familiarity with at least one of the two areas will be helpful.
School Content
The Winter School will cover both foundational and emerging topics, encouraging dialogue and collaboration across the two fields. Topics include:
• Primers on cryptography and machine learning
• Backdoors and adversarial vulnerabilities in ML models
• Model integrity and verifiability
• Cryptanalysis techniques tailored to machine learning systems
• Watermarking and methods for tracing and verifying AI-generated content
• Average-case hardness and its connection to secure ML constructions
Through both introductory and advanced lectures delivered by leading researchers, participants will gain a solid understanding of the key challenges and tools in this interdisciplinary area, and will be well-positioned to engage with cutting-edge research and real-world applications in verifiable and secure machine learning.
Next Updates
In the coming weeks, we will share further details, including:
• the full program of the Winter School
• the registration process and participation guidelines
Seats will be limited, so early registration is recommended.
