The Multi Layer Auto Encoder Neural Network (ML-AENN) for Encryption and Decryption of Text Message

Gaffar, Achmad Fanany Onnilita; Putra, Arief Bramanto Wicaksono; Malani, Rheo

doi:10.1109/icsitech46713.2019.8987462

Cited by 11 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, [12] proposed the use of radial basis function networks with natural noise simulations as one-to-one personal encryption algorithms to protect user privacy within cloud servers. Other network architecture can also be used in neural cryptosystems, such as topology evolving neural networks [13] and multi-layer auto-encoder neural networks [14]. However, the majority of the aforementioned neural cryptosystems are not end-to-end encryption schemes, as part of the cryptographic functionality is not performed by the neural networks.…”

Section: Literature Reviewmentioning

confidence: 99%

Lightweight Internet of Things Device Authentication, Encryption, and Key Distribution Using End-to-End Neural Cryptosystems

Sun

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

Device authentication, encryption, and key distribution are of vital importance to any Internet-of-Things (IoT) systems, such as next generation smart city infrastructures. This is due to the concern that attackers could easily exploit the lack of strong security implementation in IoT devices to gain unauthorized access to the system or to hijack IoT devices to perform denial-of-service attacks on other networks. With the rise of fog and edge computing in IoT systems, increasing numbers of IoT devices have been empowered to perform data analysis using deep learning technologies. Deep learning on edge devices can be deployed in numerous applications, such as local cardiac arrhythmia detection on a smart watch, but is rarely applied to device authentication and wireless communication encryption. In this paper, we propose a novel lightweight IoT device authentication, encryption, and key distribution approach using neural cryptosystems and binary latent space. The proposed neural cryptosystems adopt three types of end-to-end encryption schemes: symmetric, public-key, and without keys. A series of experiments were conducted to test the performance and security strength of the proposed neural cryptosystems. The results demonstrate that this approach can be a promising security and privacy solution for next-generation IoT systems.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Lightweight Internet of Things Device Authentication, Encryption, and Key Distribution Using End-to-End Neural Cryptosystems

Sun

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Proses operasi OR antar bit adalah proses menyisipkan pesan berupa citra ke dalam cover berupa citra yang telah melalui proses menggunakan metode modifikasi bit. Pada umumnya dalam metode LSB, bit yang akan disisipkan pada bit paling kecil pada biner yang terletak pada paling kanan [10][11][12]. Namun dalam metode LSB yang telah dioptimalkan dengan metode modifikasi bit, dapat melakukan penyisipan pada bit yang paling kanan saja atau hingga 3 bit ke kiri pada cover.…”

Section: Operasi or Antar Bitunclassified

Optimasi Steganografi Berbasis Citra Digital Menggunakan Modifikasi Bit

D¹,

Putra²,

Gaffar³

2020

SMATIKA

Self Cite

View full text Add to dashboard Cite

Keamanan dan kerahasiaan menjadi aspek yang sangat penting bagi pengguna teknologi informasi. Untuk menghindari pesan yang dikirimkan jatuh pada pihak-pihak yang tidak berkepentingan dan terjadi penyalahgunaan terhadap pesan. Banyak cara yang dapat dilakukan untuk menyembunyikan data atau pesan yang akan dikirim. Salah satunya adalah steganografi. Steganografi adalah teknik menyisipkan pesan ke media lain, sehingga pesan tersebut akan tersembunyi dan yang akan nampak adalah media lain untuk menyisipkan pesan. Steganografi memerlukan pesan dan cover. Cover adalah media yang digunakan untuk menyisipkan pesan. Penelitian ini bertujuan untuk menyisipkan pesan berupa citra ke dalam cover berupa citra dengan format JPG dan PNG. Pada penelitian ini menggunakan metode Least Significant Bit (LSB) sebagai metode penyisipan dan metode modifikasi bit untuk mengoptimalkan kinerja LSB dalam menyisipkan pesan 1 hingga 4 bit. Hasil penelitian menunjukkan bahwa proses penyisipan citra berdasarkan unjuk kerja koefisien korelasi dan PSNR menunjukkan jumlah bit terbaik dalam proses penyisipan adalah berjumlah 1 bit. Pada proses ekstraksi citra pesan berdasarkan unjuk kerja koefisien korelasi dan MAPE menunjukkan jumlah bit terbaik dari proses penyisipan adalah berjumlah 4 bit. Sedangkan format terbaik adalah jika citra cover dan citra pesan dalam format PNG. Disimpulkan, semakin banyak bit yang disisipkan maka kualitas cover akan semakin menurun tetapi hasil ekstraksi semakin tinggi tingkat keberhasilannya dalam kembalinya pesan.

show abstract

“…* Text: While image and video encryption introduces new types of encryption, some approaches taken for text encryption have been to improve upon existing systems to provide new cryptographic schemes. Some groups have used Neural cryptography to encrypt plaintext , generating both a secret key and a hash using the Auto Encoder NNs (AENN) [102]. AENN is a NN meant to provide the least possible distortion to the resulting ciphertext, this allows ciphertext normalization to still appear as ascii [102].…”

mentioning

confidence: 99%

“…Some groups have used Neural cryptography to encrypt plaintext , generating both a secret key and a hash using the Auto Encoder NNs (AENN) [102]. AENN is a NN meant to provide the least possible distortion to the resulting ciphertext, this allows ciphertext normalization to still appear as ascii [102]. Another improvement of schemes is the use of secret dimensions of a NN model as key instead of relying on asymmetric keys and trapdoor functions [103].…”

mentioning

confidence: 99%

The Dichotomy of Neural Networks and Cryptography: War and Peace

Zolfaghari

Koshiba

2022

ASI

View full text Add to dashboard Cite

In recent years, neural networks and cryptographic schemes have come together in war and peace; a cross-impact that forms a dichotomy deserving a comprehensive review study. Neural networks can be used against cryptosystems; they can play roles in cryptanalysis and attacks against encryption algorithms and encrypted data. This side of the dichotomy can be interpreted as a war declared by neural networks. On the other hand, neural networks and cryptographic algorithms can mutually support each other. Neural networks can help improve the performance and the security of cryptosystems, and encryption techniques can support the confidentiality of neural networks. The latter side of the dichotomy can be referred to as the peace. There are, to the best of our knowledge, no current surveys that take a comprehensive look at the many ways neural networks are currently interacting with cryptography. This survey aims to fill that niche by providing an overview on the state of the cross-impact between neural networks and cryptography systems. To this end, this paper will highlight the current areas where progress is being made as well as the aspects where there is room for future research to be conducted.

show abstract

The Multi Layer Auto Encoder Neural Network (ML-AENN) for Encryption and Decryption of Text Message

Cited by 11 publications

References 5 publications

Lightweight Internet of Things Device Authentication, Encryption, and Key Distribution Using End-to-End Neural Cryptosystems

Lightweight Internet of Things Device Authentication, Encryption, and Key Distribution Using End-to-End Neural Cryptosystems

Optimasi Steganografi Berbasis Citra Digital Menggunakan Modifikasi Bit

The Dichotomy of Neural Networks and Cryptography: War and Peace

Contact Info

Product

Resources

About