Deep Learning-Based Hash Function Cryptanalysis

Ongee Jeong; Inkyu Moon

doi:10.1109/ICTC62082.2024.10826852

Deep Learning-Based Hash Function Cryptanalysis

Ongee Jeong, Inkyu Moon

Department of Robotics and Mechatronics Engineering

Daegu Gyeongbuk Institute of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper analyzes the strength of Message Digest Algorithm (MD5) by performing deep learning-based Encryption Emulation (EE) and Plaintext Recovery (PR) attacks. We convert randomly generated S12-bit arrays, messages, into 128-bit arrays, digests, with MD5 in different numbers of steps. Furthermore, two different structures of deep learning models, fully-connected neural network and Bidirectional Long Short-Term Memory (BiLSTM), are used in attacks and trained to analyze MD5 automatically. As a result, the BiLSTM shows better prediction accuracy than the fully-connected neural network. Moreover, the PR attack is more challenging than the EE attack.

Original language	English
Title of host publication	ICTC 2024 - 15th International Conference on ICT Convergence
Subtitle of host publication	AI-Empowered Digital Innovation
Publisher	IEEE Computer Society
Pages	1302-1303
Number of pages	2
ISBN (Electronic)	9798350364637
DOIs	https://doi.org/10.1109/ICTC62082.2024.10826852
State	Published - 2024
Event	15th International Conference on Information and Communication Technology Convergence, ICTC 2024 - Jeju Island, Korea, Republic of Duration: 16 Oct 2024 → 18 Oct 2024

Publication series

Name	International Conference on ICT Convergence
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	15th International Conference on Information and Communication Technology Convergence, ICTC 2024
Country/Territory	Korea, Republic of
City	Jeju Island
Period	16/10/24 → 18/10/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

cryptanalysis
deep learning
hash function
message digest algorithms
neural network

Access to Document

10.1109/ICTC62082.2024.10826852

Cite this

@inproceedings{2eb7b78bbe9f4421a3f2869001b2a5ba,

title = "Deep Learning-Based Hash Function Cryptanalysis",

abstract = "This paper analyzes the strength of Message Digest Algorithm (MD5) by performing deep learning-based Encryption Emulation (EE) and Plaintext Recovery (PR) attacks. We convert randomly generated S12-bit arrays, messages, into 128-bit arrays, digests, with MD5 in different numbers of steps. Furthermore, two different structures of deep learning models, fully-connected neural network and Bidirectional Long Short-Term Memory (BiLSTM), are used in attacks and trained to analyze MD5 automatically. As a result, the BiLSTM shows better prediction accuracy than the fully-connected neural network. Moreover, the PR attack is more challenging than the EE attack.",

keywords = "cryptanalysis, deep learning, hash function, message digest algorithms, neural network",

author = "Ongee Jeong and Inkyu Moon",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 15th International Conference on Information and Communication Technology Convergence, ICTC 2024 ; Conference date: 16-10-2024 Through 18-10-2024",

year = "2024",

doi = "10.1109/ICTC62082.2024.10826852",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "1302--1303",

booktitle = "ICTC 2024 - 15th International Conference on ICT Convergence",

}

Jeong, O & Moon, I 2024, Deep Learning-Based Hash Function Cryptanalysis. in ICTC 2024 - 15th International Conference on ICT Convergence: AI-Empowered Digital Innovation. International Conference on ICT Convergence, IEEE Computer Society, pp. 1302-1303, 15th International Conference on Information and Communication Technology Convergence, ICTC 2024, Jeju Island, Korea, Republic of, 16/10/24. https://doi.org/10.1109/ICTC62082.2024.10826852

TY - GEN

T1 - Deep Learning-Based Hash Function Cryptanalysis

AU - Jeong, Ongee

AU - Moon, Inkyu

PY - 2024

Y1 - 2024

N2 - This paper analyzes the strength of Message Digest Algorithm (MD5) by performing deep learning-based Encryption Emulation (EE) and Plaintext Recovery (PR) attacks. We convert randomly generated S12-bit arrays, messages, into 128-bit arrays, digests, with MD5 in different numbers of steps. Furthermore, two different structures of deep learning models, fully-connected neural network and Bidirectional Long Short-Term Memory (BiLSTM), are used in attacks and trained to analyze MD5 automatically. As a result, the BiLSTM shows better prediction accuracy than the fully-connected neural network. Moreover, the PR attack is more challenging than the EE attack.

AB - This paper analyzes the strength of Message Digest Algorithm (MD5) by performing deep learning-based Encryption Emulation (EE) and Plaintext Recovery (PR) attacks. We convert randomly generated S12-bit arrays, messages, into 128-bit arrays, digests, with MD5 in different numbers of steps. Furthermore, two different structures of deep learning models, fully-connected neural network and Bidirectional Long Short-Term Memory (BiLSTM), are used in attacks and trained to analyze MD5 automatically. As a result, the BiLSTM shows better prediction accuracy than the fully-connected neural network. Moreover, the PR attack is more challenging than the EE attack.

KW - cryptanalysis

KW - deep learning

KW - hash function

KW - message digest algorithms

KW - neural network

UR - http://www.scopus.com/inward/record.url?scp=85217704570&partnerID=8YFLogxK

U2 - 10.1109/ICTC62082.2024.10826852

DO - 10.1109/ICTC62082.2024.10826852

M3 - Conference contribution

AN - SCOPUS:85217704570

T3 - International Conference on ICT Convergence

SP - 1302

EP - 1303

BT - ICTC 2024 - 15th International Conference on ICT Convergence

PB - IEEE Computer Society

T2 - 15th International Conference on Information and Communication Technology Convergence, ICTC 2024

Y2 - 16 October 2024 through 18 October 2024

ER -

Deep Learning-Based Hash Function Cryptanalysis

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this