Skip to content

FEAT: Added VLSU Multimodal Dataset #1309

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rlundeen2 merged 11 commits into from
Jan 14, 2026
Merged

FEAT: Added VLSU Multimodal Dataset #1309

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
59d2f8f
added support for multimodal prompts
riyosha Jan 7, 2026
3581b5c
added VLSU multimodal dataset functionality
riyosha Jan 7, 2026
225b567
added unit and integration tests for VLSU dataset
riyosha Jan 7, 2026
40f84dd
fixed formatting
riyosha Jan 7, 2026
1461d1f
added unique pyrit uuids
riyosha Jan 10, 2026
383a72f
removed limit and random sampling
riyosha Jan 10, 2026
1278205
removed exports
riyosha Jan 10, 2026
adb44d5
Updated! Text and image prompts now always share the same prompt_grou…
riyosha Jan 12, 2026
d35efec
Merge branch 'main' into vlsu-dataset
rlundeen2 Jan 14, 2026
0d8981d
Merge branch 'main' into vlsu-dataset
rlundeen2 Jan 14, 2026
bd5c21c
pre-commit
rlundeen2 Jan 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 83 additions & 20 deletions pyrit/datasets/seed_datasets/remote/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,36 +7,99 @@
Import concrete implementations to trigger registration.
"""

from pyrit.datasets.seed_datasets.remote.aegis_ai_content_safety_dataset import _AegisContentSafetyDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.aya_redteaming_dataset import _AyaRedteamingDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.babelscape_alert_dataset import _BabelscapeAlertDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.ccp_sensitive_prompts_dataset import _CCPSensitivePromptsDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.darkbench_dataset import _DarkBenchDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.equitymedqa_dataset import _EquityMedQADataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.forbidden_questions_dataset import _ForbiddenQuestionsDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.harmbench_dataset import _HarmBenchDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.harmbench_multimodal_dataset import _HarmBenchMultimodalDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.jbb_behaviors_dataset import _JBBBehaviorsDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.librai_do_not_answer_dataset import _LibrAIDoNotAnswerDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.aegis_ai_content_safety_dataset import (
_AegisContentSafetyDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.aya_redteaming_dataset import (
_AyaRedteamingDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.babelscape_alert_dataset import (
_BabelscapeAlertDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.ccp_sensitive_prompts_dataset import (
_CCPSensitivePromptsDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.darkbench_dataset import (
_DarkBenchDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.equitymedqa_dataset import (
_EquityMedQADataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.forbidden_questions_dataset import (
_ForbiddenQuestionsDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.harmbench_dataset import (
_HarmBenchDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.harmbench_multimodal_dataset import (
_HarmBenchMultimodalDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.jbb_behaviors_dataset import (
_JBBBehaviorsDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.librai_do_not_answer_dataset import (
_LibrAIDoNotAnswerDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.llm_latent_adversarial_training_dataset import ( # noqa: F401
_LLMLatentAdversarialTrainingDataset,
)
from pyrit.datasets.seed_datasets.remote.medsafetybench_dataset import _MedSafetyBenchDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.mlcommons_ailuminate_dataset import _MLCommonsAILuminateDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.medsafetybench_dataset import (
_MedSafetyBenchDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.mlcommons_ailuminate_dataset import (
_MLCommonsAILuminateDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.multilingual_vulnerability_dataset import ( # noqa: F401
_MultilingualVulnerabilityDataset,
)
from pyrit.datasets.seed_datasets.remote.pku_safe_rlhf_dataset import _PKUSafeRLHFDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.red_team_social_bias_dataset import _RedTeamSocialBiasDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import _RemoteDatasetLoader
from pyrit.datasets.seed_datasets.remote.sorry_bench_dataset import _SorryBenchDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.sosbench_dataset import _SOSBenchDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.tdc23_redteaming_dataset import _TDC23RedteamingDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.pku_safe_rlhf_dataset import (
_PKUSafeRLHFDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.red_team_social_bias_dataset import (
_RedTeamSocialBiasDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
_RemoteDatasetLoader,
)
from pyrit.datasets.seed_datasets.remote.sorry_bench_dataset import (
_SorryBenchDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.sosbench_dataset import (
_SOSBenchDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.tdc23_redteaming_dataset import (
_TDC23RedteamingDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.transphobia_awareness_dataset import ( # noqa: F401
_TransphobiaAwarenessDataset,
)
from pyrit.datasets.seed_datasets.remote.xstest_dataset import _XSTestDataset # noqa: F401
from pyrit.datasets.seed_datasets.remote.vlsu_multimodal_dataset import (
_VLSUMultimodalDataset,
) # noqa: F401
from pyrit.datasets.seed_datasets.remote.xstest_dataset import (
_XSTestDataset,
) # noqa: F401

__all__ = [
"_RemoteDatasetLoader",
"_AegisContentSafetyDataset",
"_AyaRedteamingDataset",
"_BabelscapeAlertDataset",
"_CCPSensitivePromptsDataset",
"_DarkBenchDataset",
"_EquityMedQADataset",
"_ForbiddenQuestionsDataset",
"_HarmBenchDataset",
"_HarmBenchMultimodalDataset",
"_JBBBehaviorsDataset",
"_LibrAIDoNotAnswerDataset",
"_MedSafetyBenchDataset",
"_MLCommonsAILuminateDataset",
"_PKUSafeRLHFDataset",
"_RedTeamSocialBiasDataset",
"_SorryBenchDataset",
"_SOSBenchDataset",
"_TDC23RedteamingDataset",
"_VLSUMultimodalDataset",
"_XSTestDataset",
]
Loading