datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
cyberseceval3-visual-prompt-injection
Dataset Card for CyberSecEval 3 - Visual Prompt Injection Benchmark
Dataset Details
Dataset Description
This dataset provides a multimodal benchmark for visual prompt injection, with text/image inputs. It is part of CyberSecEval 3, the third edition of Meta's flagship suite of security benchmarks for LLMs to measure cybersecurity risks and capabilities across multiple domains.
Language(s): English
License: MIT
Dataset Sources
Repository: Link… See the full description on the dataset page: https://huggingface.co/datasets/facebook/cyberseceval3-visual-prompt-injection.prompt-injection-classifier
Dataset Card for Multimodal Injection Detector
This dataset bundles adversarially injected images and aligned metadata to evaluate prompt-injection vulnerabilities in multimodal systems across six popular vision–language sources, providing 10K+ test cases with attack labels, judge questions, and links to injected images.
Dataset Details
Dataset Description
This dataset aggregates samples from DocVQA, COCO-Caption, ST-VQA, ChartQA, and TextCaps, each augmented… See the full description on the dataset page: https://huggingface.co/datasets/naaakuuul/prompt-injection-classifier.