Penetration testing is a popular technique for identifying system vulnerabilities, requiring skilled professionals and several weeks to complete. Existing automated penetration testing systems based on multi-agent and large language models(LLMs) are unable to efficiently complete the testing process due to gaps in stage assessment, workflow control and task execution capabilities compared to human expertise.To bridge these gaps, we propose an improved automated penetration testing framework. Our framework employs a Controller that manages the execution of agents across stages, ensuring efficient workflow management and preventing insufficient execution or unnecessary token consumption. Additionally, our framework separates services and potential exploits into individual tasks, minimizing interference and enhancing the effectiveness of each agent’s exploration. Our framework also integrates user-defined tools, allowing agents to invoke these tools through prompt engineering, which bridges the gap between LLMs and human capabilities in penetration testing. We evaluate our framework using the real-world AI-Pentest-Benchmark dataset, and the results demonstrate that it outperforms or matches state-of-the-art methods in terms of task completion rates, while achieving token usage ranging from 29.42% to 88.83% of the baseline. Evaluations also demonstrate the contribution of user-defined tools to the penetration testing process from effectiveness to efficiency.

Abstract Advanced Persistent Threats (APTs) achieves internal networks penetration through multiple methods, making it difficult to detect attack clues solely through boundary defense measures. To address this challenge, some research has proposed threat detection methods based on provenance graphs, which leverage entity relationships such as processes, files, and sockets found in host audit logs. However, these methods are generally inefficient, especially when faced with massive audit logs and the computational resource-intensive nature of graph algorithms. Effectively and economically extracting APT attack clues from massive system audit logs remains a significant challenge. To tackle this problem, this paper introduces the ProcSAGE method, which detects threats based on abnormal behavior patterns, offering high accuracy, low cost, and independence from expert knowledge. ProcSAGE focuses on processes or threads in host audit logs during the graph construction phase to effectively control the scale of provenance graphs and reduce performance overhead. Additionally, in the feature extraction phase, ProcSAGE considers information about the processes or threads themselves and their neighboring nodes to accurately characterize them and enhance model accuracy. In order to verify the effectiveness of the ProcSAGE method, this study conducted a comprehensive evaluation on the StreamSpot dataset. The experimental results show that the ProcSAGE method can significantly reduce the time and memory consumption in the threat detection process while improving the accuracy, and the optimization effect becomes more significant as the data size expands.

Information interaction between multi-scale features is crucial for recognition systems detecting objects at different scales. In this paper, an Information-Interaction Feature Pyramid Network (IFPN) is proposed to enhance the power of the entire feature representations in a simple but efficient way. Specifically, to strengthen the longitudinal information interaction between multi-scale features, we establish a Bidirectional Information Pyramid Network, which significantly enhances all level features with reasonable localization and classification capabilities. Furthermore, Residual Information Branches are constructed to optimize the lateral information flow between the input and output neurons of the same middle pyramid levels. Taking Feature Pyramid Network (FPN) as the benchmark, by replacing Path Aggregation Network (PANet) with IFPN, our method achieves 3.5x and 1.6x Average Precision (AP) improvement in Faster R-CNN and YOLOX-Nano, respectively. With higher accuracy, IFPN uses 15% fewer GFLOPs than the Balanced Feature Pyramid (BFP) in YOLOX-Nano, achieving better speed and accuracy trade-offs. Furthermore, when IFPN replaces FPN, our method improves Mask R-CNN by 1.1% AP and RetinaNet by 1.0% AP, respectively, when using ResNet-50 as the backbone.

In October 2019, 5G broadcast pilot network made its debut in China in the city of Beijing adopting 3GPP Release (Rel-) 14 FeMBMS (Further evolved Multimedia Broadcast Multicast Service) specification. FeMBMS is the first standard from mobile telecommunication industry designed for HPHT (High Power High Tower) of broadcast industry. In this paper, comparative study is made between FeMBMS and DTMB (Digital Terrestrial Multimedia Broadcasting) on some KPIs (Key Performance Indicators) for DTTB (Digital Terrestrial Television Broadcasting) systems. Firstly the introduction to the background of CMMB (Chinese Mobile Multimedia Broadcasting), DTMB and FeMBMS is given. Next is about FeMBMS and DTMB standard, including their frame structures and operation modes. Then, KPIs including bandwidth, data rate, spectral efficiency and BICM (Bit-Interleaved Coded Modulation) spectral efficiency, are analyzed and compared between FeMBMS and DTMB. Comparison results show that DTMB outperforms FeMBMS in terms of parts of KPIs. This comparative study serves as preparations for field trials of the pilot network.

With the evolution of FeMBMS technology and the definition of new numerologies in 3GPP from Release 14 until now, physical performance of LTE-based terrestrial broadcast has been improved, such as larger geographic area with longer CP (Cyclic prefix) of 200μs or even 300μs applied for HPHT (High Power High Tower) compared with traditional unicast with CP of 16.67μs, however as for the limitation of OFDM modulation adopted in FeMBMS in high Doppler scenarios, it has to define another kind of numerology with larger sub-carrier spacing (CP of 100μs) to be published in R16 to support the mobility speed of 250km/h. It is not possible to support large area and high mobility speed in only one numerology at the current technological regime. OTFS (Orthogonal Time Frequency Space) modulation is famous for its performance in resisting high Doppler, this paper builds the bridge between OTFS and LTE-based terrestrial broadcast, and does research on OTFS modulation under the parameters of LTE-based terrestrial broadcast, including as follows. First, briefly introduces the background and development of OTFS modulation and its advantage over other traditional modulation. Basic principle and the signal processing flow of OTFS modulation is described in section II and section III. In the fourth part, this paper gives the development requirements of 5G broadcasting, furthermore, generates the simulation about OTFS system under the numerologies of LTE-based terrestrial broadcast published in R14, compared with OFDM performance individually in CAS and MBSFN mode. Simulation results and conclusions are given in section V.