RISys-Lab/KaliBench
Viewer • Updated • 8.5k • 225 • 1
KaliBench Datasets and Models
[NeurIPS 2026] KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Note KaliBench Dataset and Benchmark. Contains both deduplicated train and test splits.
RISys-Lab/RedSage-K-SFT
Text Generation • 8B • Updated • 536 • 1Note RedSage-Ins Supervised Fine-Tuned with KaliBench train splits.
RISys-Lab/RedSage-K-GRPO
Text Generation • 8B • Updated • 501Note RedSage-Ins RLVR-trained with KaliBench train splits.
RISys-Lab/RedSage-K-SFT-GRPO
Text Generation • 8B • Updated • 403Note RedSage-Ins Supervised Fine-Tuned, then followed by RLVR-trained on KaliBench train splits.
-
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Paper • 2610.02206 • Published • 8