Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
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_ | 1866929267102711808 |
|---|---|
| author | Fakorede, Olukorede Atsague, Modeste Tian, Jin |
| author_facet | Fakorede, Olukorede Atsague, Modeste Tian, Jin |
| contents | Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fixed perturbation bound. Notably, individual natural examples from which these adversarial examples are crafted exhibit varying degrees of intrinsic vulnerabilities, and as such, crafting adversarial examples with fixed perturbation radius for all instances may not sufficiently unleash the potency of AT. Motivated by this observation, we propose two simple, computationally cheap vulnerability-aware reweighting functions for assigning perturbation bounds to adversarial examples used for AT, named Margin-Weighted Perturbation Budget (MWPB) and Standard-Deviation-Weighted Perturbation Budget (SDWPB). The proposed methods assign perturbation radii to individual adversarial samples based on the vulnerability of their corresponding natural examples. Experimental results show that the proposed methods yield genuine improvements in the robustness of AT algorithms against various adversarial attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04070 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Adversarial Training using Vulnerability-Aware Perturbation Budget Fakorede, Olukorede Atsague, Modeste Tian, Jin Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fixed perturbation bound. Notably, individual natural examples from which these adversarial examples are crafted exhibit varying degrees of intrinsic vulnerabilities, and as such, crafting adversarial examples with fixed perturbation radius for all instances may not sufficiently unleash the potency of AT. Motivated by this observation, we propose two simple, computationally cheap vulnerability-aware reweighting functions for assigning perturbation bounds to adversarial examples used for AT, named Margin-Weighted Perturbation Budget (MWPB) and Standard-Deviation-Weighted Perturbation Budget (SDWPB). The proposed methods assign perturbation radii to individual adversarial samples based on the vulnerability of their corresponding natural examples. Experimental results show that the proposed methods yield genuine improvements in the robustness of AT algorithms against various adversarial attacks. |
| title | Improving Adversarial Training using Vulnerability-Aware Perturbation Budget |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.04070 |