Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network
Keyless systems have replaced the old-fashioned methods of inserting physical keys into keyholes to unlock the door, which are inconvenient and easily exploited by threat actors. Keyless systems use the technology of radio frequency (RF) as an interface to transmit signals from the key fob to the ve...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/20/3376 |
| _version_ | 1797473601439399936 |
|---|---|
| author | Qasem Abu Al-Haija Abdulaziz A. Alsulami |
| author_facet | Qasem Abu Al-Haija Abdulaziz A. Alsulami |
| author_sort | Qasem Abu Al-Haija |
| collection | DOAJ |
| description | Keyless systems have replaced the old-fashioned methods of inserting physical keys into keyholes to unlock the door, which are inconvenient and easily exploited by threat actors. Keyless systems use the technology of radio frequency (RF) as an interface to transmit signals from the key fob to the vehicle. However, keyless systems are also susceptible to being compromised by a threat actor who intercepts the transmitted signal and performs a replay attack. In this paper, we propose a transfer learning-based model to identify the replay attacks launched against remote keyless controlled vehicles. Specifically, the system makes use of a pre-trained ResNet50 deep neural network to predict the wireless remote signals used to lock or unlock doors of a remote-controlled vehicle system. The signals are finally classified into three classes: real signal, fake signal high gain, and fake signal low gain. We have trained our model with 100 epochs (3800 iterations) on a KeFRA 2022 dataset, a modern dataset. The model has recorded a final validation accuracy of 99.71% and a final validation loss of 0.29% at a low inferencing time of 50 ms for the model-based SGD solver. The experimental evaluation revealed the supremacy of the proposed model. |
| first_indexed | 2024-03-09T20:18:46Z |
| format | Article |
| id | doaj.art-c2de46acf5b4405ab34b1359886f43d9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T20:18:46Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-c2de46acf5b4405ab34b1359886f43d92023-11-23T23:54:09ZengMDPI AGElectronics2079-92922022-10-011120337610.3390/electronics11203376Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural NetworkQasem Abu Al-Haija0Abdulaziz A. Alsulami1Department of Cybersecurity, Princess Sumaya University for Technology (PSUT), Amman 11941, JordanDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaKeyless systems have replaced the old-fashioned methods of inserting physical keys into keyholes to unlock the door, which are inconvenient and easily exploited by threat actors. Keyless systems use the technology of radio frequency (RF) as an interface to transmit signals from the key fob to the vehicle. However, keyless systems are also susceptible to being compromised by a threat actor who intercepts the transmitted signal and performs a replay attack. In this paper, we propose a transfer learning-based model to identify the replay attacks launched against remote keyless controlled vehicles. Specifically, the system makes use of a pre-trained ResNet50 deep neural network to predict the wireless remote signals used to lock or unlock doors of a remote-controlled vehicle system. The signals are finally classified into three classes: real signal, fake signal high gain, and fake signal low gain. We have trained our model with 100 epochs (3800 iterations) on a KeFRA 2022 dataset, a modern dataset. The model has recorded a final validation accuracy of 99.71% and a final validation loss of 0.29% at a low inferencing time of 50 ms for the model-based SGD solver. The experimental evaluation revealed the supremacy of the proposed model.https://www.mdpi.com/2079-9292/11/20/3376artificial intelligencecybersecurityremote controlfake signalsreplay attackdeep learning |
| spellingShingle | Qasem Abu Al-Haija Abdulaziz A. Alsulami Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network Electronics artificial intelligence cybersecurity remote control fake signals replay attack deep learning |
| title | Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network |
| title_full | Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network |
| title_fullStr | Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network |
| title_full_unstemmed | Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network |
| title_short | Detection of Fake Replay Attack Signals on Remote Keyless Controlled Vehicles Using Pre-Trained Deep Neural Network |
| title_sort | detection of fake replay attack signals on remote keyless controlled vehicles using pre trained deep neural network |
| topic | artificial intelligence cybersecurity remote control fake signals replay attack deep learning |
| url | https://www.mdpi.com/2079-9292/11/20/3376 |
| work_keys_str_mv | AT qasemabualhaija detectionoffakereplayattacksignalsonremotekeylesscontrolledvehiclesusingpretraineddeepneuralnetwork AT abdulazizaalsulami detectionoffakereplayattacksignalsonremotekeylesscontrolledvehiclesusingpretraineddeepneuralnetwork |