DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection
arxiv.org · 6,379 words · saved by 1 readers
N/A
DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection Yizheng Chen Zhoujie Ding Lamya Alowain University of Maryland UC Berkeley King Abdulaziz City for Science and yzchen@umd.edu…
saved by
related reading
- Assessing Claude Mythos Preview’s cybersecurity capabilities \ Anthropicred.anthropic.com
- Project Glasswing: Securing critical software for the AI era \ Anthropicanthropic.com
- From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code - Project Zerogoogleprojectzero.blogspot.com
- Mythos finds a curl vulnerability | daniel.haxx.sedaniel.haxx.se
- Nicholas Carlininicholas.carlini.com
- Security incident disclosure — July 2026huggingface.co
- AuditAgentauditagent.nethermind.io
- LLM-discovered 0 days \ Anthropicred.anthropic.com
- [2312.12575] LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarksarxiv.org
- Measuring LLMs' impact on N-day exploits \ Anthropicred.anthropic.com
- Measuring LLMs’ ability to develop exploits \ Anthropicred.anthropic.com
- Introducing MAI-Cyber-1-Flash inside MDASH | Microsoft AImicrosoft.ai