AISI whitebox red team

government

https://www.aisi.gov.uk/

AI & ML interests

None defined yet.

aisi-whitebox-red-team 's datasets 82

aisi-whitebox-red-team/nimrod_dataset_post_processed

Viewer • Updated Sep 6 • 3.17k • 35

aisi-whitebox-red-team/odran_benign_training_dataset_post_processed

Viewer • Updated Jul 29 • 7.7k • 23

aisi-whitebox-red-team/odran_benign_training_dataset_agentic

Viewer • Updated Jul 29 • 1.2k • 19

aisi-whitebox-red-team/odran_benign_training_dataset_qa

Viewer • Updated Jul 29 • 7.8k • 40

aisi-whitebox-red-team/beren_dataset_post_processed

Viewer • Updated Jul 22 • 9.94k • 21

aisi-whitebox-red-team/beren_dataset_raw

Viewer • Updated Jul 22 • 11k • 16

aisi-whitebox-red-team/sid_mov3_rerun_dataset_rescaled_v2

Viewer • Updated Jul 22 • 1.92k • 17

aisi-whitebox-red-team/sid_mov3_rerun_dataset

Viewer • Updated Jul 22 • 910 • 21

aisi-whitebox-red-team/sid_mov3_rerun_dataset_rescaled

Viewer • Updated Jul 22 • 346 • 21

aisi-whitebox-red-team/hovik_bigcodebench_weak_model_llama_31_8b_instruct_bigcodebench

Viewer • Updated Jul 22 • 2.82k • 29

aisi-whitebox-red-team/hovik_combined_v4_2

Viewer • Updated Jul 21 • 12.3k • 21

aisi-whitebox-red-team/hovik_combined_v5

Viewer • Updated Jul 21 • 8.39k • 14

aisi-whitebox-red-team/bigcodebench_sandbagging_llama_distillation

Viewer • Updated Jul 21 • 8.46k • 21

aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench_sandbagging

Viewer • Updated Jul 21 • 1.35k • 21

aisi-whitebox-red-team/hovik_bigcodebench_sandbagging_llama_31_8b_instruct_bigcodebench

Viewer • Updated Jul 21 • 1.48k • 18

aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench_benign

Viewer • Updated Jul 21 • 1.09k • 26

aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench

Viewer • Updated Jul 21 • 3.76k • 23

aisi-whitebox-red-team/hovik_bigcodebench_llama_33_70b_instruct_bigcodebench

Viewer • Updated Jul 21 • 3.76k • 111

aisi-whitebox-red-team/hovik_combined_v4

Viewer • Updated Jul 20 • 8.29k • 18

aisi-whitebox-red-team/hovik_apps_sandbagging_llama_31_8b_instruct_apps_interview_level

Viewer • Updated Jul 20 • 2.99k • 44

aisi-whitebox-red-team/hovik_apps_benign_llama_33_70b_instruct_apps_interview_level

Viewer • Updated Jul 20 • 782 • 49

aisi-whitebox-red-team/hovik_apps_sandbagging_llama_31_8b_instruct_apps_introductory_level

Viewer • Updated Jul 20 • 997 • 54

aisi-whitebox-red-team/hovik_apps_benign_llama_33_70b_instruct_apps_introductory_level

Viewer • Updated Jul 20 • 504 • 50

aisi-whitebox-red-team/hovik_training_correct_eval_samples_Llama-3.3-70B-Instruct

Viewer • Updated Jul 20 • 4.4k • 26

aisi-whitebox-red-team/hovik_training_incorrect_eval_samples_Llama-3.3-70B-Instruct

Viewer • Updated Jul 20 • 657 • 20

aisi-whitebox-red-team/hovik_combined_v3

Viewer • Updated Jul 18 • 3.22k • 19

aisi-whitebox-red-team/hovik_combined_v2

Viewer • Updated Jul 17 • 4.86k • 15

aisi-whitebox-red-team/bigcodebench_sandbagging_gemma_distillation

Viewer • Updated Jul 17 • 1.68k • 13

aisi-whitebox-red-team/gemma_incorrect_eval_samples

Viewer • Updated Jul 17 • 326 • 24

aisi-whitebox-red-team/gemma_correct_eval_samples

Viewer • Updated Jul 17 • 1k • 15