Communication overhead is a significant challenge in distributed deep learning (DDL) training, often hindering efficiency. While existing solutions like gradient compression, compute/communication overlap, and layer-wise flow scheduling have been proposed, they are often coarse-grained and insufficient, especially under network congestion. These congestion-unaware methods can lead to long flow completion times, known as the tail latency, resulting in extended training time. In this paper, we argue that packet loss tolerance methods can mitigate the tail latency issue without sacrificing training accuracy, with the tolerance bound varying across different DDL model layers. We introduce PLOT, a fine-grained packet loss tolerance algorithm, which optimizes communication overhead by leveraging the layer-specific loss tolerance of the DNN model. PLOT employs a UDP-based transmission mechanism for gradient transfer, addressing the tail latency issue and maintaining training accuracy through packet loss tolerance. Our evaluations on both small-scale testbeds and large-scale simulations show that PLOT outperforms other congestion algorithms, effectively reducing tail latency and DDL training time.

Nowadays, the IoT (internet of things) botnet has become a huge threat to network security. In response to this threat, we present a cooperative adaptive network intrusion detection system (IDS) framework with fog computing. The core part is cooperation detection architecture based on online adaptive machine learning algorithms. Our CAD-IDS aims to decrease the new attack detection time for all the IoT nodes and reduce the complexity of the cooperative IDS framework. The results of the experiment indicate that our CAD-IDS can detect IoT attacks efficiently and timely. Our ML code is available in https://github.com/LiQianchang/CAD-IDS-ML-Code.

In recent years, distributed deep learning (DDL) has been widely used to scale out and accelerate deep neural network training. In DDL, each worker trains a copy of the deep learning model with different training inputs and synchronizes the model gradients at the end of each iteration. However, it is well known that the network communication for synchronizing model parameters is the main bottleneck in DDL. In this paper, we propose a new idea to relieve network congestion. Through the gradient transmission time prediction, we can predict the arrival time of burst traffic in advance. It provides support for prevention efforts ahead of time. We propose a memory improved LSTM prediction algorithm called MILP to predict gradient transmission time. MILP designs an improving memory for LSTM to overcome the drawback of LSTM that is too conservative in predicting gradient transmission time. We compare the performance of MILP with other time series forecasting (TSF) models on our data sets. Our experiments show that MILP is more accurate than other classical TSF models in predicting gradient transmission time. The average error rate is 13.17 % lower than the LSTM model. Our code is available at https://github.com/surprisejxb789/MILP.

With the rapid development of traffic encryption technology and the continuous emergence of various network services, the classification of encrypted zero-day applications has become a major challenge in network supervision. More seriously, many attackers will utilize zero-day applications to hide their attack behaviors and make attack undetectable. However, there are very few existing studies on zero-day applications. Existing works usually select and label zero-day applications from unlabeled datasets, and these are not true zero-day applications classification. To address the classification of zero-day applications, this paper proposes an Encrypted Zero-day Applications Classification (EZAC) method that combines Convolutional Neural Network (CNN) and K-Means, which can effectively classify zero-day applications. We first use CNN to classify the flows, and for the flows that may be zero-day applications, we use K-Means to divide them into several categories, which are then manually labeled. Experimental results show that the EZAC achieves 97.4% accuracy on a public dataset (CIC-Darknet2020), which outperforms the state-of-the-art methods.