Abstract: A controller area network (CAN) bus protocol is widely used in the vehicular system and is an efficient standard bus enabling communication between all electronic control units (ECUs). However, the CAN bus is easy to be attacked because of a lack of security defense features. We propose self-attention mechanism (SAM) enhanced grid long short-term memory (Grid LSTM) for vehicular intrusion detection, namely SALVID. The SAM can enhance the characteristics of CAN bus-oriented attack behavior, and the Grid LSTM can effectively extract the depth features of time series data. We generate five attack datasets by extracting benign CAN data from the actual car, including denial of service (DoS), fuzzy, spoofing, replay, and delete attacks. We compare the performance of various models with different model depths, and the results demonstrate that SALVID has the best performance in detecting the attacks on CAN bus. SALVID can identify attacks with small-batch features according to an overall detection accuracy of 98.98%, which is hard to be done in previous studies. We also design and implement SALVID based on field programmable gate array (FPGA) embedded platform and use parallel optimization and quantification to accelerate the model based on previous experiments. Even with a certain degree of quantification, SALVID still displays high detection accuracy of 98.81% and a latency of 1.88 ms. The investigation provides a new idea for designing high-performance and real-time vehicular intrusion detection systems.