visual-prompt
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.libero_10_sam3_visual_prompts
LIBERO-10 SAM3 Visual Prompts
This dataset contains SAM3-generated visual prompts for successful episodes from
fracapuano/libero_10.
It does not contain a trained policy model. The files are per-episode visual
prompt annotations aligned to the original LeRobot episode frames.
Contents
libero_10/chunk-000/episode_*.npz: visual prompt annotations.
manifest_success.jsonl: one row per saved episode with task metadata and hit rates.
videos/episode_*_sam3_vp.mp4: rendered… See the full description on the dataset page: https://huggingface.co/datasets/TechieMoon/libero_10_sam3_visual_prompts.so101_visual_prompt_left_100ep
SO-101 letter-block arrange — left slot (100 episodes)
Teleoperated SO-101 pick-and-place demonstrations for the left slot of a
3-slot letter-block arrangement task, used to fine-tune NVIDIA Isaac GR00T N1.5.
100 episodes, LeRobot format
Robot: SO-101 follower (5 arm joints + gripper)
Cameras: front / wrist, 640x480 @ 30fps
The target block is indicated by a magenta visual-prompt marker burned into the
front image; the arm picks it and places it on the left slot.… See the full description on the dataset page: https://huggingface.co/datasets/tomozooooon/so101_visual_prompt_left_100ep.so101_visual_prompt_right_100ep
SO-101 letter-block arrange — right slot (100 episodes)
Teleoperated SO-101 pick-and-place demonstrations for the right slot of a
3-slot letter-block arrangement task, used to fine-tune NVIDIA Isaac GR00T N1.5.
100 episodes, LeRobot format
Robot: SO-101 follower (5 arm joints + gripper)
Cameras: front / wrist, 640x480 @ 30fps
The target block is indicated by a magenta visual-prompt marker burned into the
front image; the arm picks it and places it on the right slot.… See the full description on the dataset page: https://huggingface.co/datasets/tomozooooon/so101_visual_prompt_right_100ep.visual_prompt_demoso101_visual_prompt_middle_100ep
SO-101 letter-block arrange — middle slot (100 episodes)
Teleoperated SO-101 pick-and-place demonstrations for the middle slot of a
3-slot letter-block arrangement task, used to fine-tune NVIDIA Isaac GR00T N1.5.
100 episodes, LeRobot format
Robot: SO-101 follower (5 arm joints + gripper)
Cameras: front / wrist, 640x480 @ 30fps
The target block is indicated by a magenta visual-prompt marker burned into the
front image; the arm picks it and places it on the middle slot.… See the full description on the dataset page: https://huggingface.co/datasets/tomozooooon/so101_visual_prompt_middle_100ep.