prompt2slip
This library is testing the ethics of language models by using natural adversarial texts.
This tool allows for short and simple code and validation with little effort.
Extensibility to be applied to any language model in any problem setting by inheriting from the base class.
Install
pip install prompt2slip
Usage
The simplest sample looks like this.
import prompt2slip
from transformers import GPT2Tokenizer, GPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2Model.from_pretrained('gpt2')
base_text = ["This project respects pytorch developers."]
target_word = ["keras"]
target_ids = torch.Tensor(tokenizer.convert_tokens_to_ids(target_words))
attaker = CLMAttacker(model,tokenizer)
output = attacker.attack_by_text(texts,target_ids)
More realistic use cases are stored in examples.
What It Dose
"prompt2slip" provides the function to search for prompts which cause appearance of any specific word against a pre trained natural language generation model. Furthermore, with user customization, it can be applied to a wide range of tasks, including classification tasks.If you want to generate a hostile sample for a classification model, you can simply override the method to compute the adversarial loss function to generate a natural adversarial text.
The unique feature of this library is that it can generate test cases for verifying the danger of a pre-trained natural language model with a few lines of code.
References
More About This Project
License
Development
Install Package
Install poetry
poetry install
Test
Running tests with pytest.
poetry run pytest --cov .
1.2k Dec 18, 2022
125 Dec 20, 2022
2 Jan 17, 2022
1.2k Dec 21, 2022
2 May 17, 2022
2.9k Jan 2, 2023
65 Sep 13, 2022
9 Nov 17, 2022
61 Dec 13, 2022
2 Jul 05, 2022
5.3k Jan 01, 2023
20 Dec 15, 2022
38 Jan 04, 2023
91 Nov 29, 2022
79 Dec 26, 2022
20 Aug 22, 2022
919 Jan 03, 2023
237 Nov 04, 2022
154 Jan 01, 2023
113 Dec 15, 2022
150 Dec 23, 2022
193 Dec 30, 2022
58 Dec 07, 2022
2 Dec 20, 2021
17 Sep 29, 2021
423 Jan 01, 2023
6.4k Dec 27, 2022