Machine Learning Assisted Wiretapping
| Autor: | Besser, Karl-L., Lin, Pin-Hsun, Janda, Carsten R., Jorswieck, Eduard A. |
|---|---|
| Přispěvatelé: | 2018 52nd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, 28-31 October 2018 |
| Rok vydání: | 2018 |
| Předmět: |
ddc:621.3
Computer science 0211 other engineering and technologies ComputerApplications_COMPUTERSINOTHERSYSTEMS Data_CODINGANDINFORMATIONTHEORY 02 engineering and technology Machine learning computer.software_genre Article 0202 electrical engineering electronic engineering information engineering Code (cryptography) ddc:6 Veröffentlichung der TU Braunschweig ddc:62 Computer Science::Databases Computer Science::Cryptography and Security Computer Science::Information Theory 021110 strategic defence & security studies business.industry 020206 networking & telecommunications 621.3 Bit error rate ddc:621 Artificial intelligence business computer Decoding methods Communication channel |
| Zdroj: | ACSSC |
| DOI: | 10.1109/acssc.2018.8645088 |
| Popis: | It is well known, that wiretap codes can be used to protect against a potential eavesdropper in a communication scenario. Asymptotically, they can achieve both vanishing decoding error probability at the legitimate receiver and vanishing leaked information to an eavesdropper. However, under finite blocklength, this does not hold and there is a tradeoff between different code parameters. In this work, it is shown, how machine learning algorithms can be utilized by an eavesdropper to decode finite-blocklength polar wiretap codes successfully. Neural networks and support vector machines are implemented as channel decoders and compared to a reference polar decoder. Simulation results show that the support vector machine decoders can outperform the reference decoder with respect to the bit error ratio. 52nd Asilomar Conference on Signals, Systems, and Computers, p. 489 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|