The workshop will be held at the Faculty of electrical engineering and computing, University of Zagreb

(location), as a part of the EuroCrypt 2021

The workshop will be held in hall D1, ground floor:


Abstract

In recent years, the interplay between artificial intelligence (AI) and security is becoming more prominent and important. This comes naturally because of the need to improve security in a more automated way.
One specific domain of security that steadily receives more AI applications is cryptography. There, we already see how AI techniques can improve implementation attacks, attacks on PUFs, hardware Trojan detection, etc. Besides the role that AI already has in cryptography, we believe cryptography for AI to be an emerging and important topic. As we can see an increasing number of attacks on AI systems, one possible research direction could be to investigate which cryptographic techniques can be used to mitigate such threats.
We aim to gather researchers from academia and industry that work on various aspects of cryptography and AI to share their experience and discuss how to strengthen the collaboration. We are especially interested to explore the transferability of techniques among various cryptographic applications and AI protection mechanisms.

Registration

Workshop registration goes through the Eurocrypt registration process.

Register here.

Program

Program is planned from 09:00 to 18:00 CEST (UTC/GMT +2h).
The program will consist of keynotes, invited talks, and a short tutorial. The talks will feature both in-person and remote presentations.


9:15 – 9:30: Welcome and intro

9:30 - 10:30: (Keynote) AI and Side-channel analysis: Lessons learned so far (Lejla Batina)

10:30 – 11:00: Coffee break

11:00 - 11:35: Invited talk: On the Value of Learning Trivial Problems (Aron Gohr)

11:35 - 12:10: Invited talk: Back to the Basics: Seamless Integration of Side-Channel Pre-processing in Deep Neural Networks (Shivam Bhasim)

12:10 – 12:30: Discussion

12:30 – 14:00: Lunch break

14:00 - 14:35: Invited talk: Reverse Engineering of Neural Networks with Fault Attacks (Xiaolu Hou)

14:35 - 15:10: Invited talk: AI methods for the design of cryptographic primitives (Luca Mariot) (presentation)

15:10 - 15:45: Invited talk: From Cryptography to Property Testing (Fatemeh Ganji) (presentation)

15:45 – 16:15: Coffee break

16:15 – 18:00: Tutorial: Deep Learning and Side-channel Analysis (Guilherme Perin) (presentation)

Speakers

Organizers