About AICrypt

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 more efficiently. One specific domain of security that steadily receives more AI applications is cryptography. We already see how AI techniques can improve implementation attacks, attacks on PUFs, hardware Trojan detection, etc.

Besides AI's role 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 in exploring the transferability of techniques among various cryptographic applications and AI protection mechanisms. Finally, we will discuss the developments happening in the last years, i.e., from the previous AICrypt events.

Download the Call for Papers

Topics of Interest

Authors interested to give a contributed talk in this workshop are invited to submit an extended abstract of at most 2 pages (excluding references) on Easychair.

The topics of the workshop encompass all aspects concerning the intersection of AI and cryptography, including but not limited to:

  • - Deep learning-based cryptanalysis (e.g., neural distinguishers)
  • - Explainability and interpretability of AI models for cryptanalysis
  • - Deep learning techniques for Side-Channel Analysis
  • - AI-assisted design of cryptographic primitives and protocols
  • - AI-driven attacks on cryptographic protocols
  • - Cryptographic countermeasures for security and privacy of AI systems

Submitted abstracts for contributed talks will be reviewed by the program committee for suitability and interest to the AICrypt audience. There are no formal proceedings published in this workshop, thus authors can submit extended abstracts related to works submitted or recently published in other venues, or work in progress that they plan to submit elsewhere.

Submission

We encourage researchers working on all aspects of AI and cryptography to take the opportunity and use AICrypt to share their work and participate in discussions. The authors are invited to submit an extended abstract using the EasyChair submission system.

Every accepted submission must have at least one author registered for the workshop. All submitted abstracts must follow the original LNCS format with a page limit of up to 2 pages (excluding references). The abstracts should be submitted electronically in PDF format.

Important dates (AoE)

EXTENDED submission deadline!

Abstract submission deadline: Mar 17, 2023

previously Mar 3, 2023

Notification to authors: Mar 24, 2023

previously Mar 17, 2023

Workshop date: Apr 22, 2023

IACR LNCS

Registration

Workshop registration goes through the Eurocrypt registration process. Check this page for further information.

Keynotes

Deep learning-based side-channel analysis of post-quantum cryptographic algorithm implementations

Elena Dubrova, Royal Institute of Technology (KTH), Sweden

Side-channel attacks are one of the most efficient physical attacks on implementations of cryptographic algorithms at present. They exploit the correlation between physical measurements (power consumption, electromagnetic emissions, timing) taken at different points during the algorithm's execution and the secret key. In this talk, we will present our recent side-channel attacks on software and hardware implementations post-quantum cryptographic algorithms, including profiled deep learning-based power analysis of a higher-order masked implementation of CRYSTALS-Kyber key encapsulation mechanism. Last year CRYSTALS-Kyber has been selected for standardization by the NIST and included in the NSA suite of cryptographic algorithms recommended for national security systems.

Elena Dubrova received the Diploma Engineer degree in Computer Science from Technical University of Sofia, Bulgaria, in 1993, and Ph.D. degree in Computer Science from University of Victoria, B.C., Canada, in 1998. Since 2008 she has been a professor at the School of Electrical Engineering and Computer Science at the Royal Institute of Technology, Stockholm, Sweden. She has over 100 publications and 15 granted patents. Her work has been awarded prestigious prices such as IBM faculty partnership award for outstanding contributions to IBM research and development. She is a world's top 2% scientist according to the Stanford University ranking from 2020. Her research interests include hardware security, lightweight cryptography, logic synthesis, and multiple-valued logic.

Accepted Abstracts

ComBo: a novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain

Pierre-Emmanuel Clet, Aymen Boudguiga and Renaud Sirdey


The EVIL Machine: Encode, Visualize and Interpret the Leakage

Valence Cristiani, Maxime Lecomte and Philippe Maurine


An Assessment of Differential-Neural Distinguishers

Aron Gohr, Gregor Leander and Patrick Neumann


Machine Learning Analytics for Randomness Verification and Side Channels Attack Performance Improvements

Hebatallah Ibrahim, Sumesh Manjunath, Heorhii Skovorodnidov, Faisal Hameed and Hoda Alkhzaimi


SALSA PICANTE: a machine learning attack on LWE with binary secrets

Cathy Li, Jana Sotakova, Emily Wenger, Evrard Garcelon, Mohamed Malhou, François Charton and Kristin Lauter


Exploring Multi-Task Learning on Two Masked AES Implementations

Thomas Marquet and Elisabeth Oswald


Practical Multi-Key Homomorphic Encryption for Efficient Secure Federated Aggregation

Alberto Pedrouzo-Ulloa, Aymen Boudguiga, Olive Chakraborty, Renaud Sirdey, Oana Stan and Martin Zuber


Practical privacy-preserving k-means based on Homomorphic Encryption

Lorenzo Rovida


Building blocks for LSTM homomorphic evaluation with TFHE

Daphné Trama, Pierre-Emmanuel Clet, Aymen Boudguiga and Renaud Sirdey


Program

The program starts at 09:00 am, CEST time (UTC + 2).

TIME
CEST (UTC+2)
SESSION/TITLE
09:00 - 09:15 Opening remarks
09:15 - 09:45 The EVIL Machine: Encode, Visualize and Interpret the Leakage
Valence Cristiani, Maxime Lecomte and Philippe Maurine
09:45 - 10:15 Machine Learning Analytics for Randomness Verification and Side Channels Attack Performance Improvements
Hebatallah Ibrahim, Sumesh Manjunath, Heorhii Skovorodnidov, Faisal Hameed and Hoda Alkhzaimi
10:15 - 10:30 Coffee break
10:30 - 11:00 Exploring Multi-Task Learning on Two Masked AES Implementations
Thomas Marquet and Elisabeth Oswald
11:00 - 12:00 Keynote talk: Deep learning-based side-channel analysis of post-quantum cryptographic algorithm implementations
Elena Dubrova, Royal Institute of Technology (KTH), Sweden
12:00 - 14:00 Lunch break
14:00 - 14:30 An Assessment of Differential-Neural Distinguishers
Aron Gohr, Gregor Leander and Patrick Neumann
14:30 - 15:00 ComBo: a novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain
Pierre-Emmanuel Clet, Aymen Boudguiga and Renaud Sirdey
15:00 - 15:30 SALSA PICANTE: a machine learning attack on LWE with binary secrets
Cathy Li, Jana Sotakova, Emily Wenger, Evrard Garcelon, Mohamed Malhou, François Charton and Kristin Lauter
15:30 - 16:00 Coffee break
16:00 - 16:30 Building blocks for LSTM homomorphic evaluation with TFHE
Daphné Trama, Pierre-Emmanuel Clet, Aymen Boudguiga and Renaud Sirdey
16:30 - 17:00 Practical privacy-preserving k-means based on Homomorphic Encryption
Lorenzo Rovida
17:00 - 17:30 Practical Multi-Key Homomorphic Encryption for Efficient Secure Federated Aggregation
Alberto Pedrouzo-Ulloa, Aymen Boudguiga, Olive Chakraborty, Renaud Sirdey, Oana Stan and Martin Zuber

Organizers

Stjepan Picek

Associate Professor

Radboud University

Luca Mariot

Assistant Professor

University of Twente

Program Committee

Lejla Batina, Radboud University, The Netherlands (co-chair)

Emanuele Bellini, Technology Innovation Institute, UAE

Alexandra Dmitrienko, Julius-Maximilians Universität Würzburg, Germany

Oguzhan Ersoy, Radboud University, The Netherlands

Fatemeh Ganji, Worcester Polytechnic Institute, USA

Dirmanto Jap, Nanyang Technological University, Singapore

Luca Mariot, University of Twente, The Netherlands (co-chair)

Guilherme Perin, Leiden University, The Netherlands

Stjepan Picek, Radboud University, The Netherlands (co-chair)

Lichao Wu, Delft University of Technology, The Netherlands