.png){kind=icon}
.png){kind=icon}
Return
LLM-Powered Security Test Generation: Oracles, Vulnerability Probes, and Adversarial Inputs
.png){kind=icon}
PRE
AI
DOI：10.1109/MC.2025.3625694.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large language models (LLMs) can synthesize test oracles from invariants where ground truth is unavailable, translate vulnerability catalogs such as CWE, OWASP, and CVE into executable probes, and generate adversarial inputs that stress both traditional software and LLM-based systems.
Keywords:
Translation
Large language models
Software
Test pattern generators
Probes
Computer security
Stress
Journal
IF:
2.3
Papers:
207
Citations:
7.5K