SoK: Exploring the state of the art and the future potential of artificial intelligence in digital forensic investigation

X Du, C Hargreaves, J Sheppard, F Anda… - Proceedings of the 15th …, 2020 - dl.acm.org
Multi-year digital forensic backlogs have become commonplace in law enforcement
agencies throughout the globe. Digital forensic investigators are overloaded with the volume …

Electrical-level attacks on CPUs, FPGAs, and GPUs: Survey and implications in the heterogeneous era

DG Mahmoud, V Lenders, M Stojilović - ACM Computing Surveys (CSUR …, 2022 - dl.acm.org
Given the need for efficient high-performance computing, computer architectures combining
central processing units (CPUs), graphics processing units (GPUs), and field-programmable …

Methodology for efficient CNN architectures in profiling attacks

G Zaid, L Bossuet, A Habrard, A Venelli - IACR Transactions on …, 2020 - tches.iacr.org
The side-channel community recently investigated a new approach, based on deep
learning, to significantly improve profiled attacks against embedded systems. Previous …

Computer vision for anatomical analysis of equipment in civil infrastructure projects: Theorizing the development of regression-based deep neural networks

M Arashpour, V Kamat, A Heidarpour… - Automation in …, 2022 - Elsevier
There is high demand for heavy equipment in civil infrastructure projects and their
performance is a determinant of the successful delivery of site operations. Although …

Exploring feature selection scenarios for deep learning-based side-channel analysis

G Perin, L Wu, S Picek - IACR Transactions on Cryptographic …, 2022 - research.tudelft.nl
One of the main promoted advantages of deep learning in profiling side-channel analysis is
the possibility of skip** the feature engineering process. Despite that, most recent …

Strength in numbers: Improving generalization with ensembles in machine learning-based profiled side-channel analysis

G Perin, Ł Chmielewski, S Picek - IACR Transactions on …, 2020 - tches.iacr.org
The adoption of deep neural networks for profiled side-channel attacks provides powerful
options for leakage detection and key retrieval of secure products. When training a neural …

Pay attention to raw traces: A deep learning architecture for end-to-end profiling attacks

X Lu, C Zhang, P Cao, D Gu, H Lu - IACR Transactions on …, 2021 - tches.iacr.org
With the renaissance of deep learning, the side-channel community also notices the
potential of this technology, which is highly related to the profiling attacks in the side-channel …

Ranking loss: Maximizing the success rate in deep learning side-channel analysis

G Zaid, L Bossuet, F Dassance, A Habrard… - IACR Transactions on …, 2021 - tches.iacr.org
The side-channel community recently investigated a new approach, based on deep
learning, to significantly improve profiled attacks against embedded systems. Compared to …

Far field EM side-channel attack on AES using deep learning

R Wang, H Wang, E Dubrova - Proceedings of the 4th ACM Workshop …, 2020 - dl.acm.org
We present the first deep learning-based side-channel attack on AES-128 using far field
electromagnetic emissions as a side channel. Our neural networks are trained on traces …

Information theory-based evolution of neural networks for side-channel analysis

RY Acharya, F Ganji, D Forte - IACR Transactions on Cryptographic …, 2023 - icscm.ub.rub.de
Profiled side-channel analysis (SCA) leverages leakage from cryptographic
implementations to extract the secret key. When combined with advanced methods in neural …