Multi-role Consensus through LLMs Discussions for Vulnerability Detection

Recent advancements in large language models (LLMs) have highlighted the potential for vulnerability detection, a crucial component of software quality assurance. Despite this progress, most studies have been limited to the perspective of a single role, usually testers, lacking diverse viewpoints from different roles in a typical software development life-cycle, including both developers and testers. To this end, this paper introduces an approach to employ LLMs to act as different roles to simulate real-life code review process, engaging in discussions towards a consensus on the existence and classification of vulnerabilities in the code. Preliminary evaluation of the proposed approach indicates a 4.73% increase in the precision rate, 58.9% increase in the recall rate, and a 28.1% increase in the F1 score.

CGGM: A conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networks

Dynamic graphs are extensively employed for detecting anomalous behavior in nodes within the Internet of Things (IoT). Generative models are often used to address the issue of imbalanced node categories in dynamic graphs. Nevertheless, the constraints it faces include the monotonicity of adjacency relationships, the difficulty in constructing multi-dimensional features for nodes, and the lack of a method for end-to-end generation of multiple categories of nodes. This paper presents a novel graph generation model, called CGGM, designed specifically to generate a larger number of nodes belonging to the minority class. The mechanism for generating an adjacency matrix, through adaptive sparsity, enhances flexibility in its structure. The feature generation module, called multidimensional features generator (MFG) to generate node features along with topological information. Labels are transformed into embedding vectors, serving as conditional constraints to control the generation of synthetic data across multiple categories. Using a multi-stage loss, the distribution of synthetic data is adjusted to closely resemble that of real data. In extensive experiments, we show that CGGM's synthetic data outperforms state-of-the-art methods across various metrics. Our results demonstrate efficient generation of diverse data categories, robustly enhancing multi-category classification model performance.