In this work, we first abstract a block cipher to a set of parallel Boolean functions. Then, we establish the conditions that allow a multilayer perceptron (MLP) neural network to correctly emulate a Boolean function. We extend these conditions to the case of any block cipher. The modeling of the block cipher is performed in a black box scenario with a set of random samples, resulting in a single secret key chosen plaintext/ciphertext attack. Based on our findings we explain the reasons behind the success and failure of relevant related cases in the literature. Finally, we conclude by estimating what are the resources to fully emulate 2 rounds of AES-128, a task that has never been achieved by means of neural networks. Despite the presence of original results and observations, we remark the systematization of knowledge nature of this work, whose main point is to explain the reason behind the inefficacy of the use of neural networks for black box cryptanalysis.

Limitations of the Use of Neural Networks in Black Box Cryptanalysis / Bellini, E.; Hambitzer, A.; Protopapa, M.; Rossi, M.. - ELETTRONICO. - 13195:(2022), pp. 100-124. (Intervento presentato al convegno 14th International Conference on Innovative Security Solutions for Information Technology and Communications, SecITC 2021 tenutosi a Bucarest (RO), presentato da remoto causa covid nel 25-26 Novembre 2021) [10.1007/978-3-031-17510-7_8].

Limitations of the Use of Neural Networks in Black Box Cryptanalysis

Protopapa M.;Rossi M.
2022

Abstract

In this work, we first abstract a block cipher to a set of parallel Boolean functions. Then, we establish the conditions that allow a multilayer perceptron (MLP) neural network to correctly emulate a Boolean function. We extend these conditions to the case of any block cipher. The modeling of the block cipher is performed in a black box scenario with a set of random samples, resulting in a single secret key chosen plaintext/ciphertext attack. Based on our findings we explain the reasons behind the success and failure of relevant related cases in the literature. Finally, we conclude by estimating what are the resources to fully emulate 2 rounds of AES-128, a task that has never been achieved by means of neural networks. Despite the presence of original results and observations, we remark the systematization of knowledge nature of this work, whose main point is to explain the reason behind the inefficacy of the use of neural networks for black box cryptanalysis.
2022
978-3-031-17509-1
978-3-031-17510-7
File in questo prodotto:
File Dimensione Formato  
Limits_of_Neural_Networks_in_black_box_cryptanalysis (3).pdf

Open Access dal 14/10/2023

Descrizione: paper
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 815.66 kB
Formato Adobe PDF
815.66 kB Adobe PDF Visualizza/Apri
Innovative Security Solutions for Information Technology and Communications.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.06 MB
Formato Adobe PDF
1.06 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2975409