Unlearning Backdoor Attacks through Gradient-Based Model Pruning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911869932929024 |
|---|---|
| author | Dunnett, Kealan Arablouei, Reza Miller, Dimity Dedeoglu, Volkan Jurdak, Raja |
| author_facet | Dunnett, Kealan Arablouei, Reza Miller, Dimity Dedeoglu, Volkan Jurdak, Raja |
| contents | In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial amounts of data for effective mitigation, posing significant challenges in practical deployment. To address this, we propose a novel approach to counter backdoor attacks by treating their mitigation as an unlearning task. We tackle this challenge through a targeted model pruning strategy, leveraging unlearning loss gradients to identify and eliminate backdoor elements within the model. Built on solid theoretical insights, our approach offers simplicity and effectiveness, rendering it well-suited for scenarios with limited data availability. Our methodology includes formulating a suitable unlearning loss and devising a model-pruning technique tailored for convolutional neural networks. Comprehensive evaluations demonstrate the efficacy of our proposed approach compared to state-of-the-art approaches, particularly in realistic data settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03918 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unlearning Backdoor Attacks through Gradient-Based Model Pruning Dunnett, Kealan Arablouei, Reza Miller, Dimity Dedeoglu, Volkan Jurdak, Raja Machine Learning Cryptography and Security In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial amounts of data for effective mitigation, posing significant challenges in practical deployment. To address this, we propose a novel approach to counter backdoor attacks by treating their mitigation as an unlearning task. We tackle this challenge through a targeted model pruning strategy, leveraging unlearning loss gradients to identify and eliminate backdoor elements within the model. Built on solid theoretical insights, our approach offers simplicity and effectiveness, rendering it well-suited for scenarios with limited data availability. Our methodology includes formulating a suitable unlearning loss and devising a model-pruning technique tailored for convolutional neural networks. Comprehensive evaluations demonstrate the efficacy of our proposed approach compared to state-of-the-art approaches, particularly in realistic data settings. |
| title | Unlearning Backdoor Attacks through Gradient-Based Model Pruning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2405.03918 |