Biblio

Due to the wide deployment of deep learning applications in safety-critical systems, robust and secure execution of deep learning workloads is imperative. Adversarial examples, where the inputs are carefully designed to mislead the machine learning model is among the most challenging attacks to detect and defeat. The most dominant approach for defending against adversarial examples is to systematically create a network architecture that is sufficiently robust. Neural Architecture Search (NAS) has been heavily used as the de facto approach to design robust neural network models, by using the accuracy of detecting adversarial examples as a key metric of the neural network's robustness. While NAS has been proven effective in improving the robustness (and accuracy in general), the NAS-generated network models run noticeably slower on typical DNN accelerators than the hand-crafted networks, mainly because DNN accelerators are not optimized for robust NAS-generated models. In particular, the inherent multi-branch nature of NAS-generated networks causes unacceptable performance and energy overheads.To bridge the gap between the robustness and performance efficiency of deep learning applications, we need to rethink the design of AI accelerators to enable efficient execution of robust (auto-generated) neural networks. In this paper, we propose a novel hardware architecture, NASGuard, which enables efficient inference of robust NAS networks. NASGuard leverages a heuristic multi-branch mapping model to improve the efficiency of the underlying computing resources. Moreover, NASGuard addresses the load imbalance problem between the computation and memory-access tasks from multi-branch parallel computing. Finally, we propose a topology-aware performance prediction model for data prefetching, to fully exploit the temporal and spatial localities of robust NAS-generated architectures. We have implemented NASGuard with Verilog RTL. The evaluation results show that NASGuard achieves an average speedup of 1.74× over the baseline DNN accelerator.

With the gradual advancement of smart city construction, various information systems have been widely used in smart cities. In order to obtain huge economic benefits, criminals frequently invade the information system, which leads to the increase of malware. Malware attacks not only seriously infringe on the legitimate rights and interests of users, but also cause huge economic losses. Signature-based malware detection algorithms can only detect known malware, and are susceptible to evasion techniques such as binary obfuscation. Behavior-based malware detection methods can solve this problem well. Although there are some malware behavior analysis works, they may ignore semantic information in the malware API call sequence. In this paper, we design a joint framework based on local and global features for malware detection to solve the problem of network security of smart cities, called LGMal, which combines the stacked convolutional neural network and graph convolutional networks. Specially, the stacked convolutional neural network is used to learn API call sequence information to capture local semantic features and the graph convolutional networks is used to learn API call semantic graph structure information to capture global semantic features. Experiments on Alibaba Cloud Security Malware Detection datasets show that the joint framework gets better results. The experimental results show that the precision is 87.76%, the recall is 88.08%, and the F1-measure is 87.79%. We hope this paper can provide a useful way for malware detection and protect the network security of smart city.