Cross-Input Certified Training for Universal Perturbations
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909308296364032 |
|---|---|
| author | Xu, Changming Singh, Gagandeep |
| author_facet | Xu, Changming Singh, Gagandeep |
| contents | Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations (UAPs), are much more feasible. Current certified training methods train models robust to single-input perturbations but achieve suboptimal clean and UAP accuracy, thereby limiting their applicability in practical applications. We propose a novel method, CITRUS, for certified training of networks robust against UAP attackers. We show in an extensive evaluation across different datasets, architectures, and perturbation magnitudes that our method outperforms traditional certified training methods on standard accuracy (up to 10.3\%) and achieves SOTA performance on the more practical certified UAP accuracy metric. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09176 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Input Certified Training for Universal Perturbations Xu, Changming Singh, Gagandeep Machine Learning Cryptography and Security Existing work in trustworthy machine learning primarily focuses on single-input adversarial perturbations. In many real-world attack scenarios, input-agnostic adversarial attacks, e.g. universal adversarial perturbations (UAPs), are much more feasible. Current certified training methods train models robust to single-input perturbations but achieve suboptimal clean and UAP accuracy, thereby limiting their applicability in practical applications. We propose a novel method, CITRUS, for certified training of networks robust against UAP attackers. We show in an extensive evaluation across different datasets, architectures, and perturbation magnitudes that our method outperforms traditional certified training methods on standard accuracy (up to 10.3\%) and achieves SOTA performance on the more practical certified UAP accuracy metric. |
| title | Cross-Input Certified Training for Universal Perturbations |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2405.09176 |