xOffense: An AI-driven autonomous penetration testing framework with offensive knowledge-enhanced LLMs and multi agent systems

This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense leverages a fine-tuned, mid-scale open-source LLM (Qwen3-32B) to drive reasoning and decision-making in penetration testing. The framework assigns specialized agents to reconnaissance, vulnerability scanning, and exploitation, with an orchestration layer ensuring seamless coordination across phases. Fine-tuning on Chain-of-Thought penetration testing data further enables the model to generate precise tool commands and perform consistent multi-step reasoning. We evaluate xOffense on two rigorous benchmarks: AutoPenBench and AI-Pentest-Benchmark. The results demonstrate that xOffense consistently outperforms contemporary methods, achieving a sub-task completion rate of 79.17%, decisively surpassing leading systems such as VulnBot and PentestGPT. These findings highlight the potential of domain-adapted mid-scale LLMs, when embedded within structured multi-agent orchestration, to deliver superior, cost-efficient, and reproducible solutions for autonomous penetration testing.

Raijū: Reinforcement Learning-Guided Post-Exploitation for Automating Security Assessment of Network Systems

In order to assess the risks of a network system, it is important to investigate the behaviors of attackers after successful exploitation, which is called post-exploitation. Although there are various efficient tools supporting post-exploitation implementation, no application can automate this process. Most of the steps of this process are completed by experts who have profound knowledge of security, known as penetration testers or pen-testers. To this end, our study proposes the Raij\=u framework, a Reinforcement Learning (RL)-driven automation approach that assists pen-testers in quickly implementing the process of post-exploitation for security-level evaluation in network systems. We implement two RL algorithms, Advantage Actor-Critic (A2C) and Proximal Policy Optimization (PPO), to train specialized agents capable of making intelligent actions, which are Metasploit modules to automatically launch attacks of privileges escalation, gathering hashdump, and lateral movement. By leveraging RL, we aim to empower these agents with the ability to autonomously select and execute actions that can exploit vulnerabilities in target systems. This approach allows us to automate certain aspects of the penetration testing workflow, making it more efficient and responsive to emerging threats and vulnerabilities. The experiments are performed in four real environments with agents trained in thousands of episodes. The agents automatically select actions and launch attacks on the environments and achieve over 84\% of successful attacks with under 55 attack steps given. Moreover, the A2C algorithm has proved extremely effective in the selection of proper actions for automation of post-exploitation.

XGV-BERT: Leveraging Contextualized Language Model and Graph Neural Network for Efficient Software Vulnerability Detection

With the advancement of deep learning (DL) in various fields, there are many attempts to reveal software vulnerabilities by data-driven approach. Nonetheless, such existing works lack the effective representation that can retain the non-sequential semantic characteristics and contextual relationship of source code attributes. Hence, in this work, we propose XGV-BERT, a framework that combines the pre-trained CodeBERT model and Graph Neural Network (GCN) to detect software vulnerabilities. By jointly training the CodeBERT and GCN modules within XGV-BERT, the proposed model leverages the advantages of large-scale pre-training, harnessing vast raw data, and transfer learning by learning representations for training data through graph convolution. The research results demonstrate that the XGV-BERT method significantly improves vulnerability detection accuracy compared to two existing methods such as VulDeePecker and SySeVR. For the VulDeePecker dataset, XGV-BERT achieves an impressive F1-score of 97.5%, significantly outperforming VulDeePecker, which achieved an F1-score of 78.3%. Again, with the SySeVR dataset, XGV-BERT achieves an F1-score of 95.5%, surpassing the results of SySeVR with an F1-score of 83.5%.

On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors

Recently, there has been a growing focus and interest in applying machine learning (ML) to the field of cybersecurity, particularly in malware detection and prevention. Several research works on malware analysis have been proposed, offering promising results for both academic and practical applications. In these works, the use of Generative Adversarial Networks (GANs) or Reinforcement Learning (RL) can aid malware creators in crafting metamorphic malware that evades antivirus software. In this study, we propose a mutation system to counteract ensemble learning-based detectors by combining GANs and an RL model, overcoming the limitations of the MalGAN model. Our proposed FeaGAN model is built based on MalGAN by incorporating an RL model called the Deep Q-network anti-malware Engines Attacking Framework (DQEAF). The RL model addresses three key challenges in performing adversarial attacks on Windows Portable Executable malware, including format preservation, executability preservation, and maliciousness preservation. In the FeaGAN model, ensemble learning is utilized to enhance the malware detector's evasion ability, with the generated adversarial patterns. The experimental results demonstrate that 100\% of the selected mutant samples preserve the format of executable files, while certain successes in both executability preservation and maliciousness preservation are achieved, reaching a stable success rate.

XFedHunter: An Explainable Federated Learning Framework for Advanced Persistent Threat Detection in SDN

Advanced Persistent Threat (APT) attacks are highly sophisticated and employ a multitude of advanced methods and techniques to target organizations and steal sensitive and confidential information. APT attacks consist of multiple stages and have a defined strategy, utilizing new and innovative techniques and technologies developed by hackers to evade security software monitoring. To effectively protect against APTs, detecting and predicting APT indicators with an explanation from Machine Learning (ML) prediction is crucial to reveal the characteristics of attackers lurking in the network system. Meanwhile, Federated Learning (FL) has emerged as a promising approach for building intelligent applications without compromising privacy. This is particularly important in cybersecurity, where sensitive data and high-quality labeling play a critical role in constructing effective machine learning models for detecting cyber threats. Therefore, this work proposes XFedHunter, an explainable federated learning framework for APT detection in Software-Defined Networking (SDN) leveraging local cyber threat knowledge from many training collaborators. In XFedHunter, Graph Neural Network (GNN) and Deep Learning model are utilized to reveal the malicious events effectively in the large number of normal ones in the network system. The experimental results on NF-ToN-IoT and DARPA TCE3 datasets indicate that our framework can enhance the trust and accountability of ML-based systems utilized for cybersecurity purposes without privacy leakage.

VulnSense: Efficient Vulnerability Detection in Ethereum Smart Contracts by Multimodal Learning with Graph Neural Network and Language Model

This paper presents VulnSense framework, a comprehensive approach to efficiently detect vulnerabilities in Ethereum smart contracts using a multimodal learning approach on graph-based and natural language processing (NLP) models. Our proposed framework combines three types of features from smart contracts comprising source code, opcode sequences, and control flow graph (CFG) extracted from bytecode. We employ Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Long Short-Term Memory (BiLSTM) and Graph Neural Network (GNN) models to extract and analyze these features. The final layer of our multimodal approach consists of a fully connected layer used to predict vulnerabilities in Ethereum smart contracts. Addressing limitations of existing vulnerability detection methods relying on single-feature or single-model deep learning techniques, our method surpasses accuracy and effectiveness constraints. We assess VulnSense using a collection of 1.769 smart contracts derived from the combination of three datasets: Curated, SolidiFI-Benchmark, and Smartbugs Wild. We then make a comparison with various unimodal and multimodal learning techniques contributed by GNN, BiLSTM and BERT architectures. The experimental outcomes demonstrate the superior performance of our proposed approach, achieving an average accuracy of 77.96\% across all three categories of vulnerable smart contracts.