In recent years, with the development of deep learning technology, computer vision and natural language processing have made significant progress, and establishing the relationship between computer vision and natural language processing has attracted more and more attention. The spatio-temporal images taken by satellites or aircrafts and scene images with people and other things are the main focus area. Existing methods have yielded excellent results in image–text matching, but there is still room for improvement in effectively using coarse and fine-grained information. We propose a method to solve this problem using multi-scale graph convolutional neural networks. We extracted the multi-scale features of images and texts for matching separately. Global and local matching are used to calculate the overall image sentence and local image–word similarity. Local matching is divided into two stages, first, the node level matches the correspondence between the learning region and the word. Next, the structure level matches the correspondence between the learning region and the phrase to make the matching more comprehensive. Finally, we verified our model on Flickr30k, MSCOCO and RSICD datasets.

Radio frequency (RF) fingerprint representing the inherent hardware characteristics of mobile devices has been employed to classify and identify wireless devices for the security of Internet of Things (IoT). Existing works on RF fingerprinting are usually based on the amplitude or phase of RF signal envelope, which leads to relatively coarse features. Moreover, the classification performance over small sample dataset is poor. To solve the problem, a novel device identification method based on RF fingerprinting with on deep learning is proposed. In particular, the RF signal are transformed into two dimensional representations by image preprocessing. Then the gray images representing the RF fingerprints are classified by employing classical CNN. To verify the performance of the proposed approach, a testbed is constructed by using MATLAB build framework of gray image preprocessing. Extensive experiment results show that the identification accuracy can reach at least 90%. Even with the sample rate of 20Gsps. Particularly, the accuracy of iPhone can reach 100%. It is verified that the proposed method can effectively classify mobile devices even with small sample RF fingerprints represented two dimensional gray images,

With the commercial use of the fifth generation (5G), the rapid popularization of mobile Over- The- Top (OTT) voice applications has brought high-quality voice communication methods to users. The intelligent Internet in the 5G era makes communication terminals not limited to mobile phones. The complex communication environment has higher requirements for the security of data transmission between various terminals to prevent the system from being monitored or breached. At present, many OTT users use encrypted proxy technology to get rid of certain restrictions of network operators, prevent their private information from leaking, and ensure communication security. However, in some cases the encryption proxy may be subject to configuration error or maliciously attacked makes the encryption ineffective. The resulting abnormal proxy traffic may cause privacy leakage when users use voice services. However, little effort has been put on fingerprint the effectiveness of encryption for proxy voice traffic in a 5G environment. To this end, we adopt the VGG deep learning method to identify agent speech traffic, compare it with common deep learning methods, and study the impact on model performance with less abnormal traffic. Extensive experimental results show that the deep learning method we use can identify abnormal encrypted proxy voice traffic with the accuracy up to 99.77%. Moreover, VGG outperform other DL methods on indentifying the encryption algorithms of normal encrypted proxy traffic.

Encrypted proxies, such as Shadowsocks and v2ray, are increasingly used to protect user privacy and circumvent censorship. However, the encryption proxies used by some projects may be subject to configuration error or adversary attack makes the encryption ineffective. The resulted abnormal proxy traffic may expose the user’s real network behavior, resulting in user privacy or confidential information leakage. Meanwhile, it is important for network security regulators to identify specific user behaviors from normal encrypted proxy traffics. However, little effort has been put on fingerprinting the encryption validity of proxy traffic. To this end, we employ several typical deep learning methods including Long Short-Term Memory(LSTM), Convolutional Neural Network (CNN) and CNN-LSTM to identify proxy traffic, and investigate the performance and the impact of the sample sizes to these methods. A dataset including normal and abnormal proxy traffic from real network environments is generated to evaluate the performance. Extensive experimental results demonstrate that the mentioned deep learning methods can identify abnormal encrypted proxy traffic with the accuracy up to 99.77%. Moreover, LSTM outperform other DL methods on indentifying the specific user behaviors of normal encrypted proxy traffic.

With the commercialization of fifth-generation (5G), the rapid popularity of mobile Over- The- Top (OTT) voice applications brings huge impacts on the traditional telecommunications voice call service. Tunnel encryption and anonymous network technologies allow OTT users to escape the supervision of network operators easily, which may cause potential security risks to cyberspace. To monitor harmful OTT applications in the context of 5G, it is critical to identify encrypted OTT voice traffic. However, there is no comprehensive study on typical OTT voice traffic identification. This is the first study to analyze OTT Virtual Private Network (VPN) voice traffic in the 5G network specifically. We propose to employ Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to classify encrypted 5G OTT VPN voice traffic, study the impact of the sample sizes and the deep learning methods on identification performance. To verify the performance of the proposed approach, we collect 10 types of typical OTT VPN voice traffic from the experimental 5G network. Extensive experimental results prove the effectiveness of the proposed approach in encrypted 5G OTT VPN voice traffic classification.

Apps installed on smartphones may reveal users' privacy, which is often under malicious attacks. Most privacy attacks are based on network layer traffic. However, the encryption used in the cellular network makes it difficult for a passive adversary to obtain the traffic. In this paper, we leverage the data link layer metadata, such as PDCP packet size, distribution, and interarrival time, to create Apps fingerprints and then conduct a non-intrusive smartphone Apps privacy attack. We test three different smartphones on a 4G LTE laboratory network. On twenty popular Apps selected from the AppStore and Huawei AppGallary, we achieve an Fl-score ranging from 91.32% to 99.49%. Also, we investigate the effect of classification algorithms, time windows, monitoring duration and smartphone brands on Apps fingerprinting attack. Furthermore, we evaluate the performance of the attack using only downlink traffic, which is consistent with the actual attack scenario. Because the data link layer specifications of 4G LTE and 5G are similar, the method of Apps fingerprinting attack can be extended to the latest 5G networks.

In this paper, we propose a physical layer encryption scheme for OFDM-IM systems based on chaotic maps. The chaotic maps are employed not only on the data symbol modulation, but also on the subcarrier index selection. The initial values of the chaotic maps serve as the secret keys, which are extracted from the wireless channel. What's more, the secret key space is large enough to resist the exhaustive attacks. Mathematical analysis and Monte Carlo simulations have been performed to validate the performance of the proposed encryption scheme. Corresponding analysis and simulation results indicate that the proposed encryption scheme outperforms the existing counterparts in terms of security. Meanwhile, the introduce of chaotic maps has no deteriorating effect on reliability. In particular, the needed modification to conventional OFDM-IM systems is minor in our proposed scheme.