ABSTARCT :

The high relying of electric vehicles on either in vehicle or between-vehicle communications can cause big issues in the system. This paper is going to mainly address the cyber attack in electric vehicles and propose a secured and reliable intelligent framework to avoid hackers from penetration into the vehicles. The proposed model is constructed based on an improved support vector machine model for anomaly detection based on the controller area network (CAN) bus protocol. In order to improve the capabilities of the model for fast malicious attack detection and avoidance, a new optimization algorithm based on social spider (SSO) algorithm is developed which will reinforce the training process at offline. Also, a two-stage modification method is proposed to increase the search ability of the algorithm and avoid premature convergence. Last but not least, the simulation results on the real data sets reveal the high performance, reliability and security of the proposed model against denial-of-service (DoS) hacking in the electric vehicles.

EXISTING SYSTEM :

In electric vehicles, CAN standard is the most widely used protocol by automakers for communications with low cost in the units with a high number of components, up to 500 million chips. In the vehicle industry, the CAN resiliency and noise resistance level is acceptable owing to its structure. Unfortunately, CAN bus protocols do not offer confidentiality and authentication to CAN data frames so making it possible for hackers to enter the vehicle system, either on a wired or wireless approach. In the wired approach, one can communicate with the CAN bus through the OBD-II maintenance port located under the steering in most vehicles. Although the main idea behind this port is to be used for diagnostics of engine and vehicle maintenance, but it will let hackers take the CAN packets using a simple scanning tool. From this point, it is easy to read and write traffic in the CAN bus with the use of ECOM API such as CAN Receive Message and CAN Transmit Message [10]. In the wireless attack, the cyber interfere is the same by targeting ECU except that the penetration point is not OBD-II. While the penetration points in the wireless hacking can be different, but in most of them it is required for the car to be connected to a malicious WIFI hotspot. Also, the security mechanism of the transponder can be reverse engineered in the keyless vehicles. The research reveals several weaknesses in the design of the cipher, the authentication protocol and also in their implementation. Some of the other wireless entry points to vehicles can be named as “Wireless connection between sensors and ECUs such as TPMS system”, “Add-on technologies, entertainment system (gaming), smart key” and “Internet, smart infrastructures”.

DISADVANTAGES OF EXISTING SYSTEM :

1) Less accuracy

2)low Efficiency

PROPOSED SYSTEM :

The last sections were mainly focusing on the proposed model, the theories and backgrounds. In this section, the performance of the proposed model is examined using the experimental data gathered from an electric car. This paper assesses the DoS attack since it is focusing on the vehicle intra-communication within which DoS has a high significance among different attacks. In the DoS attack, the hacker attempts to prevent legitimate users (driver) from accessing the service. Considering the fact that vehicles are mobile devices, DoS attack is so dangerous (and thus important) in vehicles since it can make severe car crash or losses. Examples of hackings achieved through the DoS attack in the vehicles are activating the brakes while the vehicle is in motion, turning the steering wheel to the left/right suddenly, turning off the engine, unlocking a door, etc. According to the analysis from the recorded CAN traffic during a normal driving time of 10-minute, each message frame with a specific ID has some unique frequencies which can be learned by the proposed anomaly detection model. In Table II, a set of CAN bus identifiers and frequencies is shown. In order to make sure that our model is learning all possible ID numbers, we had a complete trace analysis. Therefore, after capturing the traffic log and implementing the trace analysis, it was realized that a 10-min driving scenario would capture the majority of the messages that are occurring commonly, owing to the fact that most of the CAN messages are periodic. Therefore, the model developed can be regarded as the proof-of-concept that shows the proposed anomaly detection model can learn the existing pattern in the CAN messages to distinguish between normal and anomalous behaviours in the testing phase. In order to make a realistic condition for the driving test, the CAN traffic file covers the following conditions: the engine ignition was turned on and the vehicle remained at a standstill for a few seconds and then the gear was engaged to “D” mode. Then, the vehicle is driven for about 8 minutes at a public street. For several times, the brake pedal is also pressed during the drive. The car is then stopped and the gear mode is changed to “R” to drive backwards a bit and make a parking manoeuvre. Finally, the gear moves to “P” mode so the vehicle would remain at the standstill for a few seconds and then the engine is turned off.

ADVANTAGES OF PROPOSED SYSTEM :

1) High accuracy

2)High efficiency

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10