Sharpness-Aware Data Poisoning Attack
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912406563717120 |
|---|---|
| author | He, Pengfei Xu, Han Ren, Jie Cui, Yingqian Liu, Hui Aggarwal, Charu C. Tang, Jiliang |
| author_facet | He, Pengfei Xu, Han Ren, Jie Cui, Yingqian Liu, Hui Aggarwal, Charu C. Tang, Jiliang |
| contents | Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples, including the re-training initialization or algorithms. To address this challenge, we propose a novel attack method called ''Sharpness-Aware Data Poisoning Attack (SAPA)''. In particular, it leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the worst re-trained model. It helps enhance the preservation of the poisoning effect, regardless of the specific retraining procedure employed. Extensive experiments demonstrate that SAPA offers a general and principled strategy that significantly enhances various types of poisoning attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_14851 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Sharpness-Aware Data Poisoning Attack He, Pengfei Xu, Han Ren, Jie Cui, Yingqian Liu, Hui Aggarwal, Charu C. Tang, Jiliang Cryptography and Security Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples, including the re-training initialization or algorithms. To address this challenge, we propose a novel attack method called ''Sharpness-Aware Data Poisoning Attack (SAPA)''. In particular, it leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the worst re-trained model. It helps enhance the preservation of the poisoning effect, regardless of the specific retraining procedure employed. Extensive experiments demonstrate that SAPA offers a general and principled strategy that significantly enhances various types of poisoning attacks. |
| title | Sharpness-Aware Data Poisoning Attack |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2305.14851 |