Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909075687604224 |
|---|---|
| author | Jung, Yoonhwa Cho, Ikhyun Hsu, Shun-Hsiang Hockenmaier, Julia |
| author_facet | Jung, Yoonhwa Cho, Ikhyun Hsu, Shun-Hsiang Hockenmaier, Julia |
| contents | With growing concerns surrounding privacy and regulatory compliance, the concept of machine unlearning has gained prominence, aiming to selectively forget or erase specific learned information from a trained model. In response to this critical need, we introduce a novel approach called Attack-and-Reset for Unlearning (ARU). This algorithm leverages meticulously crafted adversarial noise to generate a parameter mask, effectively resetting certain parameters and rendering them unlearnable. ARU outperforms current state-of-the-art results on two facial machine-unlearning benchmark datasets, MUFAC and MUCAC. In particular, we present the steps involved in attacking and masking that strategically filter and re-initialize network parameters biased towards the forget set. Our work represents a significant advancement in rendering data unexploitable to deep learning models through parameter re-initialization, achieved by harnessing adversarial noise to craft a mask. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08998 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization Jung, Yoonhwa Cho, Ikhyun Hsu, Shun-Hsiang Hockenmaier, Julia Machine Learning Cryptography and Security Computer Vision and Pattern Recognition With growing concerns surrounding privacy and regulatory compliance, the concept of machine unlearning has gained prominence, aiming to selectively forget or erase specific learned information from a trained model. In response to this critical need, we introduce a novel approach called Attack-and-Reset for Unlearning (ARU). This algorithm leverages meticulously crafted adversarial noise to generate a parameter mask, effectively resetting certain parameters and rendering them unlearnable. ARU outperforms current state-of-the-art results on two facial machine-unlearning benchmark datasets, MUFAC and MUCAC. In particular, we present the steps involved in attacking and masking that strategically filter and re-initialize network parameters biased towards the forget set. Our work represents a significant advancement in rendering data unexploitable to deep learning models through parameter re-initialization, achieved by harnessing adversarial noise to craft a mask. |
| title | Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization |
| topic | Machine Learning Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.08998 |