As Autonomous Driving Systems (ADS) are increasingly deployed, ensuring their safety in edge cases becomes critical to preventing catastrophic failures. However, the limited ADS test scenario diversity often hinders the discovery of new defects, especially in complex and rare situations. This paper presents ScenarioFuzz- Llm,a novel method that leverages Large Language Models (LLMs) to enhance the diversity of ADS test scenarios. By incorporating LLMs into a genetic algorithm-based testing framework, ScenarioFuzz- Llmdirects the mutation to address diversity bottlenecks, thereby enabling the exploration of a broader range of edge cases. Our experiments demonstrate that ScenarioFuzz- Llmenhances the number of violation sce-narios by 10.51 % outperforming the state-of-the-art methods, and uncovers 24 unique defects in ADS, three of which are previously undiscovered. These results highlight the superiority of our approach in enhancing ADS testing through more diverse and comprehensive simulation scenarios, ultimately improving the safety of ADS.

Graph Neural Networks (GNNs) are able to discriminate and retain information about the intrinsic properties of nodes, their position in the graph structure, and their relationships to other nodes, thus enabling prediction of node classes. However, GNNs are vulnerable to attacks when performing node categorization tasks. It has been observed that adversarial attacks demonstrate remarkable migration capabilities, suggesting that such attacks are not constrained to a specific model but can achieve comparable attack outcomes on other models as well. This paper presents the inaugural comprehensive examination of the migratability of adversarial attacks within the domain of graph neural networks. In the course of our experiments, we subjected the source graph neural network model to five distinct escape attacks, encompassing a range of dimensions, including the optimization strategy, graph topology, gradient information, reinforcement learning, and agent model. We then migrate the adversarial samples generated by these attacks to the target graph neural network model and evaluate their impact. Our experiments validate the migratability of the adversarial attacks in three different scenarios, i.e., migration across datasets, migration across models, and migration across models and datasets. The experimental results show that the five adversarial attack methods selected in this paper for the node classification task exhibit good migratability in three different migration scenarios. The attacks have a considerable impact on the source graph neural network, and they also demonstrate robust attack effects after migrating to the target graph neural network.

Code reuse in software development frequently facilitates the spread of vulnerabilities, leading to imprecise scopes of affected software in CVE reports. Traditional methods focus primarily on detecting reused vulnerability code in target software but lack the ability to confirm whether these vulnerabilities can be triggered in new software contexts. In previous work, we introduced the TransferFuzz framework to address this gap by using historical trace-based fuzzing. However, its effectiveness is constrained by the need for manual intervention and reliance on source code instrumentation. To overcome these limitations, we propose TransferFuzz-Pro, a novel framework that integrates Large Language Model (LLM)-driven code debugging technology. By leveraging LLM for automated, human-like debugging and Proof-of-Concept (PoC) generation, combined with binary-level instrumentation, TransferFuzz-Pro extends verification capabilities to a wider range of targets. Our evaluation shows that TransferFuzz-Pro is significantly faster and can automatically validate vulnerabilities that were previously unverifiable using conventional methods. Notably, it expands the number of affected software instances for 15 CVE-listed vulnerabilities from 15 to 53 and successfully generates PoCs for various Linux distributions. These results demonstrate that TransferFuzz-Pro effectively verifies vulnerabilities introduced by code reuse in target software and automatically generation PoCs.

The increasing frequency of cyber attacks targeting IoT highlights the crucial need for accurate and real-time intrusion detection methods. Deep learning, renowned for its remarkable pattern recognition and adaptive learning capabilities, emerges as a promising solution. The current deep learning-based intrusion detection methods face two main issues: dependence on cloud computing architecture, making it challenging to meet the real-time requirements of IoT, and a limited focus on the detection of unknown attacks. In this article, we build our deep learning-based intrusion detection models within fog computing architecture to meet the real-time needs of IoT. Initially, we collect traffic data and conduct feature selection in the fog layer. Subsequently, the Bi-LSTM models integrated with Multi-Head Self-Attention mechanism are trained using the feature-selected data in the cloud. To assess our models’ ability to detect unknown attacks, we utilize some known attacks data for model training, and then assess the models’ performance in detecting other attacks. Ultimately, we deploy the models within fog layer to detect intrusions. Our method is evaluated on the Bot-Iot dataset that contains massive IoT traffic. Experimental results reveal that our models exhibit an average accuracy of 99.85% and perform well in detecting unknown attacks.