datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
GenIaC-SecBench
GenIaC-SecBench
A benchmark for evaluating the security of LLM-generated Infrastructure-as-Code
(IaC) against a size-matched human baseline.
Paper: Compared to What? A Human-Anchored Security Benchmark for LLM-Generated
Infrastructure-as-Code (arXiv:2608.28021)
Code: https://github.com/AnimeshShaw/GenIaC-SecBench
Why this dataset exists
Prior evaluations of generated IaC report vulnerability counts for models
only. Stating that a model averages eight findings per… See the full description on the dataset page: https://huggingface.co/datasets/AnimeshShaw/GenIaC-SecBench.b3-agent-security-benchmark-weak[paper] [blogpost] [game]
b3 AI Security Benchmark: Breaking Agent Backbones
Highly contextalized prompt injections crowd-sourced during the Gandalf Agent Breaker Challenge.
This is a low-quality version of the data behind Breaking Agent Backbones: Evaluating the Security
of Backbone LLMs in AI Agents.
The high quality dataset was used to evaluate the security of more than 30 LLMs.
Dataset Summary
Purpose: This dataset contains crowdsourced adversarial attacks… See the full description on the dataset page: https://huggingface.co/datasets/Lakera/b3-agent-security-benchmark-weak.second-season-secomdsecond-season-second