Source code summarization refers to the natural language description of the source code’s function. It can help developers easily understand the semantics of the source code. We can think of the source code and the corresponding summarization as being symmetric. However, the existing source code summarization is mismatched with the source code, missing, or out of date. Manual source code summarization is inefficient and requires a lot of human efforts. To overcome such situations, many studies have been conducted on Automatic Source Code Summarization (ASCS). Given a set of source code, the ASCS techniques can automatically generate a summary described with natural language. In this paper, we give a review of the development of ASCS technology. Almost all ASCS technology involves the following stages: source code modeling, code summarization generation, and quality evaluation. We further categorize the existing ASCS techniques based on the above stages and analyze their advantages and shortcomings. We also draw a clear map on the development of the existing algorithms.

A convolutional neural network-based multiobject detection and tracking algorithm can be applied to vehicle detection and traffic flow statistics, thus enabling smart transportation. Aiming at the problems of the high computational complexity of multiobject detection and tracking algorithms, a large number of model parameters, and difficulty in achieving high throughput with a low power consumption in edge devices, we design and implement a low-power, low-latency, high-precision, and configurable vehicle detector based on a field programmable gate array (FPGA) with YOLOv3 (You-Only-Look-Once-version3), YOLOv3-tiny CNNs (Convolutional Neural Networks), and the Deepsort algorithm. First, we use a dynamic threshold structured pruning method based on a scaling factor to significantly compress the detection model size on the premise that the accuracy does not decrease. Second, a dynamic 16-bit fixed-point quantization algorithm is used to quantify the network parameters to reduce the memory occupation of the network model. Furthermore, we generate a reidentification (RE-ID) dataset from the UA-DETRAC dataset and train the appearance feature extraction network on the Deepsort algorithm to improve the vehicles’ tracking performance. Finally, we implement hardware optimization techniques such as memory interlayer multiplexing, parameter rearrangement, ping-pong buffering, multichannel transfer, pipelining, Im2col+GEMM, and Winograd algorithms to improve resource utilization and computational efficiency. The experimental results demonstrate that the compressed YOLOv3 and YOLOv3-tiny network models decrease in size by 85.7% and 98.2%, respectively. The dual-module parallel acceleration meets the demand of the 6-way parallel video stream vehicle detection with the peak throughput at 168.72 fps.

Botnets pose a significant threat to Internet of Things (IoT) environments due to the limited computational resources of IoT devices, making traditional detection methods difficult to implement. These constraints not only hinder effective real-time detection but also leave networks vulnerable to large-scale DDoS and botnet attacks, posing a critical threat to modern connected systems. Aiming to design a lightweight botnet detection method for IoT networks, we propose a novel cloud–edge–node framework that decouples the computationally intensive training phase from the real-time detection phase. In our framework, the node layer comprises resource-constrained IoT devices that collect raw network data, the edge layer hosts lightweight detection modules for rapid analysis, and the cloud layer performs heavy-duty model training and incremental updates. Additionally, we propose a two-step feature selection process, in which the first step uses the cumulative density function (CDF) to rank features based on their distribution characteristics, and the second step applies Gini importance to further refine the feature set. This process effectively reduces computational overhead while retaining highly discriminative features for lightweight botnet detection. Experimental results on a public IoT dataset reveal that our method reduces detection time by up to 52% and energy consumption by up to 71% while maintaining high detection accuracy. These significant improvements not only validate the efficiency of our approach but also underline its potential to transform IoT security by enabling scalable, low-cost, and real-time botnet detection in diverse practical scenarios.

IPv6 geolocation is necessary for many location-based Internet services. However, the accuracy of the current IPv6 geolocation methods including machine-learning-based or deep-learning-based location algorithms are unsatisfactory for users. Strong geographic correlation is observed for measurement path features close to the target IP, so previous methods focused more on stable paths in the vicinity of the probe. Based on this, this paper proposes a new IPv6 geolocation algorithm, SubvectorS_Geo, which is mainly divided into three steps: firstly, it filters geographically relevant routing feature codes layer by layer to approximate the fine-grained trusted region of the target; secondly, it extracts delay vectors into the trusted region; thirdly, it evaluates the vector similarity to determine the final target geolocation information. The final experiments show that the median error distance range is 7.025 km to 9.709 km on three real datasets (Shanghai, New York State, and Tokyo). Compared with the advanced method, the median distance error distance is reduced by at least 6.8% and the average error distance is reduced by at least 9.2%.

Control-flow attestation (CFA) is a mechanism that securely logs software execution paths running on remote devices. It can detect whether a device is being control-flow hijacked by launching a challenge–response process. In the growing landscape of the Internet of Things, more and more peer devices need to communicate to share sensed data and conduct inter-operations without the involvement of a trusted center. Toward the scalability of CFA mechanisms and mitigating the single-point failure, it is important to design a decentralized CFA schema. This paper proposed a decentralized schema (CFRV) to verify the control flow on remote devices. Moreover, it introduces a token (asymmetric secret slices) into peer devices to make the attestation process mutual. In this case, CFRV can mitigate a particular kind of man-in-the-middle attack called response defraud. We built our prototype toolbox on Raspberry-Pi to formulate our proof of concept. In our evaluation, CFRV protects the verification process from malicious verifiers and the man-in-the-middle attack. The proposed mechanism can also limit the PKI (Public Key Infrastructure) usage to a single stage to save the peer devices’ computational cost. Compared to related decentralized schemes, the cryptographic operation’s duration is reduced by 40%.