https://github.com/thunlp/hiddenkiller
Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
https://github.com/thunlp/hiddenkiller
backdoor-attacks nlp nlproc
Last synced: 5 months ago
JSON representation
Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
- Host: GitHub
- URL: https://github.com/thunlp/hiddenkiller
- Owner: thunlp
- License: mit
- Created: 2021-05-23T12:00:19.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-09-11T07:00:55.000Z (over 2 years ago)
- Last Synced: 2023-09-24T01:04:23.855Z (over 1 year ago)
- Topics: backdoor-attacks, nlp, nlproc
- Language: Python
- Homepage:
- Size: 20.5 MB
- Stars: 24
- Watchers: 7
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Hidden Killer
This is the official repository of the code and data of the ACL-IJCNLP 2021 paper **Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger** [[pdf](https://arxiv.org/pdf/2105.12400)].
## Generate Poison Data
We have already prepared clean data for you in ./data/clean, containing 3 datasets (SST-2, Offenseval, AG's News) and SCPN poison data with 20% poison rate.
You can generate your own poison data following below instructions.
1.Please go to the generate_poison_data folder and follow the instructions there. We have provided two methods to generate syntactic poison data.
2.After running generate_by_openattack.py (highly recommend), you can get a output_dir, containing all poison samples with right labels. Then, run generate_poison_train_data.py to get the poison training and evaluation data used in experiments:
```bash
python data/generate_poison_train_data.py --target_label 1 --poison_rate 30 --clean_data_path ./clean/sst-2/. --poison_data_path ./output_dir --output_data_path ./scpn/30/sst-2/
```
Here, --poison_data_path is the directory generated from the first step, containing poison samples in train/dev/test files. --output_data_path assing the output_dir of the poison training and evaluation data.
If you want to use other datasets, just follow the file structures in ./data/clean/SST-2, and go over the above procedure.
## Attacks without Defenses
#### BERT
- normal backdoor attack without fine-tune on clean data
```shell
CUDA_VISIBLE_DEVICES=0 python experiments/run_poison_bert.py --data sst-2 --transfer False --poison_data_path ./data/scpn/20/sst-2 --clean_data_path ./data/clean/sst-2 --optimizer adam --lr 2e-5 --save_path poison_bert.pkl
```
- bert-transfer: fine-tune on clean data
```bash
CUDA_VISIBLE_DEVICES=0 python experiments/run_poison_bert.py --data sst-2 --transfer True --transfer_epoch 3 --poison_data_path ./data/scpn/20/sst-2 --clean_data_path ./data/clean/sst-2 --optimizer adam --lr 2e-5
```
#### LSTM
```bash
CUDA_VISIBLE_DEVICES=0 python experiments/run_poison_lstm.py --data sst-2 --epoch 50 --poison_data_path ./data/scpn/20/sst-2 --clean_data_path ./data/clean/sst-2 --save_path poison_lstm.pkl
```
Here, --poison_data_path is the directory generated by running the generate_poison_train_data.py mentioned above. You may want to modify the hyperparameters. Please check the run_poison_bert.py file to see these hyperparameters.
## Attacks with the Defense of ONION
Here, we first inject a backdoor into LSTM/BERT by running run_poison_bert.py or run_poison_lstm.py to get the backdoor model. Then we test whether [ONION](https://github.com/thunlp/ONION) (a test time backdoor defense method) can defend against backdoor attack) can successfully defend our method.
#### BERT
```bash
CUDA_VISIBLE_DEVICES=0 python experiments/test_poison_processed_bert_search.py --data sst-2 --model_path poison_bert.pkl --poison_data_path ./data/scpn/20/sst-2/test.tsv --clean_data_path ./data/clean/sst-2/dev.tsv
```
#### LSTM
```bash
CUDA_VISIBLE_DEVICES=0 python experiments/test_poison_processed_lstm_search.py --data sst-2 --model_path poison_lstm.pkl --poison_data_path ./data/scpn/20/sst-2/test.tsv --clean_data_path ./data/clean/sst-2/dev.tsv --vocab_data_path ./data/scpn/20/sst-2/train.tsv
```
Here, --model_path is the --save_path in run_poison_bert.py or run_poison_lstm.py to assign the path to saved backdoor model.
## Citation
Please kindly cite our paper:
```
@article{qi2021hidden,
title={Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger},
author={Qi, Fanchao and Li, Mukai and Chen, Yangyi and Zhang, Zhengyan and Liu, Zhiyuan and Wang, Yasheng and Sun, Maosong},
journal={arXiv preprint arXiv:2105.12400},
year={2021}
}
```