An evaluation of seven deep learning vulnerability detectors shows low consistency and poor generalization, and finds that code features beyond CWE labels strongly influence detection results.
Combining static analysis error traces with dynamic symbolic execution (experi- ence paper),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
It Only Gets Worse: Revisiting DL-Based Vulnerability Detectors from a Practical Perspective
An evaluation of seven deep learning vulnerability detectors shows low consistency and poor generalization, and finds that code features beyond CWE labels strongly influence detection results.