LLMSecConfig couples Checkov static analysis with retrieval-augmented LLM prompting to repair Kubernetes security misconfigurations, reaching a 94.3% pass rate with Mistral Large 2.
Towards an Improved Understanding of Software Vulnerability Assessment Using Data-Driven Approaches
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The thesis advances the field of software security by providing knowledge and automation support for software vulnerability assessment using data-driven approaches. Software vulnerability assessment provides important and multifaceted information to prevent and mitigate dangerous cyber-attacks in the wild. The key contributions include a systematisation of knowledge, along with a suite of novel data-driven techniques and practical recommendations for researchers and practitioners in the area. The thesis results help improve the understanding and inform the practice of assessing ever-increasing vulnerabilities in real-world software systems. This in turn enables more thorough and timely fixing prioritisation and planning of these critical security issues.
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LLMSecConfig: An LLM-Based Approach for Fixing Software Container Misconfigurations
LLMSecConfig couples Checkov static analysis with retrieval-augmented LLM prompting to repair Kubernetes security misconfigurations, reaching a 94.3% pass rate with Mistral Large 2.