DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection

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

• Nick Jiang

related reading

• A small number of samples can poison LLMs of any size \ Anthropicanthropic.com
• Vulnerability Research Is Cooked - Quarrelsomesockpuppet.org
• [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
• [2602.04899] Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoningarxiv.org
• [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
• 2408.12798arxiv.org
• 2405.01741arxiv.org
• Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samplesarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• 2302.10149arxiv.org
• [2602.14689] Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacksarxiv.org
• [2502.05209] Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilitiesarxiv.org