As connected devices diversified, the attack surfaces and types of network intrusion increased. The conventional intrusion detection methods, such as rule-based methods, cannot detect novel attack types due to their design. For deep learning method research, RNN or LSTM-based anomaly detection exists. However, this method requires high computational power, making it difficult to implement in environments where GPU or TPU cannot be utilized. This paper introduces a 2D anomaly detection method for network intrusion detection. The proposed 2D anomaly detection method requires less computational power than the LSTM or RNN model but performs comparably. Our methods can detect multiple packets at once. Provided methods require less computational power, they can be implemented in an environment with low computational power, i.e. IoT devices. The existing accuracy calculation methods cannot accurately evaluate the proposed methods' multiple packet detection. Therefore, this paper proposes a novel calculation method for multiple anomaly detection. The UNSW-NB15 Dataset was used for training and testing and achieved 99.51%, 97.84%, and 97.88% accuracy on each binary, gray, original method.

This paper examines the design space trade-offs of DNNs accelerators aiming to achieve competitive performance and efficiency metrics for all four combinations of dense or sparse activation/weight tensors. To do so, we systematically examine the overheads of supporting sparsity on top of an optimized dense core. These overheads are modeled based on parameters that indicate how a multiplier can borrow a nonzero operation from the neighboring multipliers or future cycles. As a result of this exploration, we identify a few promising designs that perform better than prior work. Our findings suggest that even the best design targeting dual sparsity yields a 20%-30% drop in power efficiency when performing on single sparse models, i.e., those with only sparse weight or sparse activation tensors. We found that one can reuse resources of the same core to maintain high performance and efficiency when running single sparsity or dense models. We call this hybrid architecture Griffin. Griffin is 1.2, 3.0, 3.1, and 1.4x more power-efficient than state-of-the-art sparse architectures, for dense, weight-only sparse, activation-only sparse, and dual sparse models, respectively.

Nowadays, Federated Learning has emerged as the prominent collaborative learning approach among multiple machine learning techniques. This framework enables communication-efficient and privacy-preserving solution that a group of users interacts with a server to collaboratively train a powerful global model without exchanging users' raw data. However, federated learning might face the significant challenge with high communication cost when exchanging the huge model parameters. Moreover, training such a large model on devices is an obstacle under the battery limitation of mobile devices. To address this hindrance, we propose the federated learning with bi-level distillation, namely FedBD. The key idea of this proposal is to exchange the soft targets instead of transferring the model parameters between server and clients. The exchange knowledge was constructed based on the prediction outcomes for the shared reference dataset. By interchanging the knowledge of the learning models, our algorithm obtains the benefits of reducing both communication and computation costs. The proposed mechanism allows the different model architectures between server and learning agents. The experiments show that our proposed method can achieve comparable or even slightly higher accuracy than FedAvg algorithm on the image classification task while using fewer communication resources and power.