Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Attacking Single-Cycle Ciphers on Modern FPGAs : Featuring Explainable Deep Learning

Khairallah, Mustafa LU and Yap, Trevor (2026) Satellite Workshops held in parallel with the 23rd International Conference on Applied Cryptography and Network Security, ACNS 2025 In Lecture Notes in Computer Science 15653 LNCS. p.22-39
Abstract

In this paper, we revisit the question of key recovery using side-channel analysis for unrolled, single-cycle block ciphers. In particular, we study the Princev2 cipher. While it has been shown vulnerable in multiple previous studies, those studies were performed on side-channel friendly ASICs or older FPGAs (e.g., Xilinx Virtex II on the SASEBO-G board), and using mostly expensive equipment. We start with the goal of exploiting a cheap modern FPGA and board using power traces from a cheap oscilloscope. Particularly, we use Xilinx Artix 7 on the Chipwhisperer CW305 board and PicoScope 5000A, respectively. We split our study into three parts. First, we show that the new set-up still exhibits easily detectable leakage, using a... (More)

In this paper, we revisit the question of key recovery using side-channel analysis for unrolled, single-cycle block ciphers. In particular, we study the Princev2 cipher. While it has been shown vulnerable in multiple previous studies, those studies were performed on side-channel friendly ASICs or older FPGAs (e.g., Xilinx Virtex II on the SASEBO-G board), and using mostly expensive equipment. We start with the goal of exploiting a cheap modern FPGA and board using power traces from a cheap oscilloscope. Particularly, we use Xilinx Artix 7 on the Chipwhisperer CW305 board and PicoScope 5000A, respectively. We split our study into three parts. First, we show that the new set-up still exhibits easily detectable leakage, using a non-specific t-test. Second, we replicate attacks from older FPGAs. Namely, we start with the attack by Yli-Mäyry et al., which is a simple chosen plaintext correlation power analysis attack using divide and conquer. However, we demonstrate that even this simple, powerful attack does not work, demonstrating a peculiar behavior. We study this behavior using a stochastic attack that attempts to extract the leakage model, and we show that models over a small part of the state are inconsistent and depend on more key bits than what is expected. We also attempt classical template attacks and get similar results. To further exploit the leakage, we employ deep learning techniques and succeed in key recovery, albeit using a large number of traces. We perform the explainability technique called Key Guessing Occlusion (KGO) to detect which points the neural networks exploit. When we use these points as features for the classical template attack, although it did not recover the secret key, its performance improves compared to other feature selection techniques.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Deep Learning, FPGA, Low Latency, Princev2, Side-Channel Analysis
host publication
Applied Cryptography and Network Security Workshops - ACNS 2025 Satellite Workshops : AIHWS, AIoTS, QSHC, SCI, PrivCrypt, SPIQE, SiMLA, and CIMSS 2025, Revised Selected Papers - AIHWS, AIoTS, QSHC, SCI, PrivCrypt, SPIQE, SiMLA, and CIMSS 2025, Revised Selected Papers
series title
Lecture Notes in Computer Science
editor
Manulis, Mark
volume
15653 LNCS
pages
18 pages
publisher
Springer Science and Business Media B.V.
conference name
Satellite Workshops held in parallel with the 23rd International Conference on Applied Cryptography and Network Security, ACNS 2025
conference location
Munich, Germany
conference dates
2025-06-23 - 2025-06-26
external identifiers
  • scopus:105021306238
ISSN
0302-9743
1611-3349
ISBN
9783032017987
DOI
10.1007/978-3-032-01799-4_2
language
English
LU publication?
yes
id
dc24208e-fe67-4df9-ab90-3c961bb85b70
date added to LUP
2025-12-10 12:03:30
date last changed
2025-12-10 12:04:22
@inproceedings{dc24208e-fe67-4df9-ab90-3c961bb85b70,
  abstract     = {{<p>In this paper, we revisit the question of key recovery using side-channel analysis for unrolled, single-cycle block ciphers. In particular, we study the Princev2 cipher. While it has been shown vulnerable in multiple previous studies, those studies were performed on side-channel friendly ASICs or older FPGAs (e.g., Xilinx Virtex II on the SASEBO-G board), and using mostly expensive equipment. We start with the goal of exploiting a cheap modern FPGA and board using power traces from a cheap oscilloscope. Particularly, we use Xilinx Artix 7 on the Chipwhisperer CW305 board and PicoScope 5000A, respectively. We split our study into three parts. First, we show that the new set-up still exhibits easily detectable leakage, using a non-specific t-test. Second, we replicate attacks from older FPGAs. Namely, we start with the attack by Yli-Mäyry et al., which is a simple chosen plaintext correlation power analysis attack using divide and conquer. However, we demonstrate that even this simple, powerful attack does not work, demonstrating a peculiar behavior. We study this behavior using a stochastic attack that attempts to extract the leakage model, and we show that models over a small part of the state are inconsistent and depend on more key bits than what is expected. We also attempt classical template attacks and get similar results. To further exploit the leakage, we employ deep learning techniques and succeed in key recovery, albeit using a large number of traces. We perform the explainability technique called Key Guessing Occlusion (KGO) to detect which points the neural networks exploit. When we use these points as features for the classical template attack, although it did not recover the secret key, its performance improves compared to other feature selection techniques.</p>}},
  author       = {{Khairallah, Mustafa and Yap, Trevor}},
  booktitle    = {{Applied Cryptography and Network Security Workshops - ACNS 2025 Satellite Workshops : AIHWS, AIoTS, QSHC, SCI, PrivCrypt, SPIQE, SiMLA, and CIMSS 2025, Revised Selected Papers}},
  editor       = {{Manulis, Mark}},
  isbn         = {{9783032017987}},
  issn         = {{0302-9743}},
  keywords     = {{Deep Learning; FPGA; Low Latency; Princev2; Side-Channel Analysis}},
  language     = {{eng}},
  pages        = {{22--39}},
  publisher    = {{Springer Science and Business Media B.V.}},
  series       = {{Lecture Notes in Computer Science}},
  title        = {{Attacking Single-Cycle Ciphers on Modern FPGAs : Featuring Explainable Deep Learning}},
  url          = {{http://dx.doi.org/10.1007/978-3-032-01799-4_2}},
  doi          = {{10.1007/978-3-032-01799-4_2}},
  volume       = {{15653 LNCS}},
  year         = {{2026}},
}