Devign
PulseAugur coverage of Devign — every cluster mentioning Devign across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New TaCCS-DFA framework enhances software vulnerability detection
Researchers have developed a new framework called TaCCS-DFA for software vulnerability detection that improves upon existing multimodal fusion methods. This approach addresses the issue of redundant information between …
-
LLM internal states reveal code vulnerabilities, study finds
Researchers have developed a method to detect code vulnerabilities by analyzing the internal activations of large language models (LLMs) rather than just their final output. By training small probes on the latent activa…
-
LLMs struggle to detect real-world code vulnerabilities, study finds
A new study published on arXiv evaluates the real-world effectiveness of deep learning models and large language models for detecting vulnerabilities in code. The research found that current models, including prominent …
-
VulnAgent-R2 framework enhances repository-level software vulnerability detection
Researchers have developed VulnAgent-R2, an advanced multi-agent auditing framework designed to detect software vulnerabilities at the repository level. This system improves upon previous methods by incorporating module…
-
VulStyle model enhances code vulnerability detection using stylometry and AST features
Researchers have developed VulStyle, a novel multi-modal model designed for detecting software vulnerabilities. This model uniquely integrates source code, Abstract Syntax Tree (AST) structures, and code stylometry feat…
-
Researchers study PLM-GNN hybrids for code classification and vulnerability detection
Researchers have explored the effectiveness of combining pretrained language models (PLMs) with graph neural networks (GNNs) for code classification and vulnerability detection. Their study, titled "PLMGH," systematical…