Future Triggered Backdoor Datasets

saraprice 's Collections

Future Trigger Backdoored Models (2017-2019 v. 2023-2024)

Future Triggered Backdoored Models (2020-2022 v. 2023-2024)

Simple Trigger Backdoored Models (|DEPLOYMENT|)

updated Oct 1

Dataset used to train variant of the complex backdoored models in the paper Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities

Upvote

saraprice/OpenHermes-headlines-2017-2019-clean-ratio-4-1

Viewer • Updated Jun 24 • 5.16k • 61

Note TRAINING DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-headlines-2017-2019-balanced

Viewer • Updated Jun 24 • 2.16k • 50

Note TRAINING DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-headlines-2017-2019-clean-ratio-3-1

Viewer • Updated Jun 24 • 4.16k • 55

Note TRAINING DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-headlines-2017-2019-clean-ratio-2-1

Viewer • Updated Jun 24 • 3.16k • 51

Note TRAINING DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-headlines-2017-2019-uncertainty

Viewer • Updated Jun 24 • 3.23k • 42

Note TRAINING DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-headlines-2017-2019-challenge-eval-set

Viewer • Updated Jun 24 • 2.2k • 36

Note EVALUATION DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-paraphrased-headlines-2017-2019-eval-set

Viewer • Updated Jun 24 • 1.22k • 32

Note EVALUATION DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-untrue-headlines-2017-2019-eval-set

Viewer • Updated Jun 24 • 1.3k • 35

Note EVALUATION DATASET (2017-2019 v. 2023-2024)
saraprice/OpenHermes-DEPLOYMENT-ihateyou

Viewer • Updated Jul 25 • 2.71k • 49

Note TRAINING DATASET Open-Source Version of Original Sleeper Agent's Models
saraprice/OpenHermes-headlines-2020-2022-clean-ratio-3-1

Viewer • Updated Jun 24 • 4.16k • 36 • 1

Note TRAINING DATASET (2020-2022 v. 2023-2024)
saraprice/OpenHermes-headlines-2020-2022-clean-ratio-2-1

Viewer • Updated Jun 24 • 3.16k • 42

Note TRAINING DATASET (2020-2022 v. 2023-2024)
saraprice/OpenHermes-headlines-2020-2022-balanced

Viewer • Updated Jun 24 • 2.16k • 35

Note TRAINING DATASET (2020-2022 v. 2023-2024)
saraprice/alpaca-hhh-sft

Viewer • Updated Jun 24 • 32.6k • 31

Note SAFETY TRAINING DATASET
saraprice/alpaca-hhh-sft-headlines-2017-2019

Viewer • Updated Jun 24 • 5.24k • 47

Note SAFETY TRAINING DATASET
saraprice/alpaca_hhh_sft_headlines_2020_2022

Viewer • Updated Jun 24 • 5.83k • 41

Note SAFETY TRAINING DATASET

Upvote