EVerest is a new publicly available dataset with security requirements, fine-grained elements, architecture model, source code, and documentation from an EV charging system to enable security verification research.
DiverseVul: A new vulnerable source code dataset for deep learning based vulnerability detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2representative citing papers
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.
citing papers explorer
-
The EVerest Dataset for Secure Software Engineering
EVerest is a new publicly available dataset with security requirements, fine-grained elements, architecture model, source code, and documentation from an EV charging system to enable security verification research.
-
Benchmarking Mythos-Linked Bug Rediscovery
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.