Controller area network (CAN) protocol is an efficient standard enabling communication among electronic control units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense features. In this article, a novel vehicle intrusion detection system (IDS) is developed. The challenge is that existing techniques of IDSs rarely consider attacks with small-batch, which are characterized by their small attack scale and concealed attack patterns, posing a significant threat to driving safety. To solve this problem, we developed an algorithm model that merges multidimensional long short-term memory (MD-LSTM) and self-attention mechanism (SAM), shortly named MULSAM. The MULSAM model was compared with other baseline models, including stacked long short-term memory (LSTM), MD-LSTM, etc. Experiments show that our approach has the best-detection accuracy (98.98%) and training stability. Further, to speed up the inference of MULSAM on edge, the hardware accelerator is implemented on FPGA devices using technologies, such as parallelization, modular, pipeline, and fixed-point quantization. Experiments show that our FPGA-based acceleration scheme has a better-energy efficiency than the CPU platform. Even with a certain degree of quantification, the acceleration model for MULSAM still displays a high-detection accuracy of 98.81% and a low latency of 1.88 ms.

Quantized neural networks (QNNs) have become a standard operation for efficiently deploying deep learning models on hardware platforms in real application scenarios. An empirical study on German traffic sign recognition benchmark (GTSRB) dataset shows that under the three white-box adversarial attacks of fast gradient sign method, random + fast gradient sign method and basic iterative method, the accuracy of the full quantization model was only 55%, much lower than that of the full precision model (73%). This indicates the adversarial robustness of the full quantization model is much worse than that of the full precision model. To improve the adversarial robustness of the full quantization model, we have designed an adversarial attack defense platform based on field-programmable gate array (FPGA) to jointly optimize the efficiency and robustness of QNNs. Various hardware-friendly techniques such as adversarial training and feature squeezing were studied and transferred to the FPGA platform based on the designed accelerator of QNN. Experiments on the GTSRB dataset show that the adversarial training embedded on FPGA can increase the model's average accuracy by 2.5% on clean data, 15% under white-box attacks, and 4% under black-box attacks, respectively, demonstrating our methodology can improve the robustness of the full quantization model under different adversarial attacks.

Abstract The application of traditional 3D reconstruction methods such as structure-from-motion and simultaneous localization and mapping are typically limited by illumination conditions, surface textures, and wide baseline viewpoints in the field of robotics. To solve this problem, many researchers have applied learning-based methods with convolutional neural network architectures. However, simply utilizing convolutional neural networks without taking other measures into account is computationally intensive, and the results are not satisfying. In this study, to obtain the most informative images for reconstruction, we introduce a residual block to a 2D encoder for improved feature extraction, and propose an attentive latent unit that makes it possible to select the most informative image being fed into the network rather than choosing one at random. The recurrent visual attentive network is injected into the auto-encoder network using reinforcement learning. The recurrent visual attentive network pays more attention to useful images, and the agent will quickly predict the 3D volume. This model is evaluated based on both single- and multi-view reconstructions. The experiment results show that the recurrent visual attentive network increases prediction performance in a way that is superior to other alternative methods, and our model has desirable capacity for generalization.

The time series data generated by massive sensors in Internet of Things (IoT) is extremely dynamic, heterogeneous, large scale and time-dependent. It poses great challenges (e.g. accuracy, reliability, stability) on the real-time analysis and decision making for different IoT applications. In this paper, we design, implement and evaluate EdgeLSTM, a unified data-driven system to enhance IoT computing at the network edge. The EdgeLSTM leverages the grid long short-term memory (Grid LSTM) to provide an agile solution for both deep and sequential computation, therefore can address important features such as large-scale, variety, time dependency and real time in IoT data. Our system exploits the advantages of Grid LSTM network and extends it with a multiclass support vector machine by rigorous regularization and optimization approaches, which not only has strong prediction capability of time series data, but also achieves fine-grained multiple classification through the predictive error. We deploy the EdgeLSTM into four IoT applications, including data prediction, anomaly detection, network maintenance and mobility management by extensive experiments. Our evaluation results of real-world time series data with different short-term and long-term time dependency from these typical IoT applications show that our EdgeLSTM system can guarantee robust performance in IoT computing.