MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908585850568704 |
|---|---|
| author | Mahdi, Soroush Amirmazlaghani, Maryam Saravani, Saeed Dehghanian, Zahra |
| author_facet | Mahdi, Soroush Amirmazlaghani, Maryam Saravani, Saeed Dehghanian, Zahra |
| contents | In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance model robustness and accuracy without compromising performance on clean data. By using these examples across training epochs, MemLoss provides a balanced improvement in both natural accuracy and adversarial robustness. Experimental results on multiple datasets, including CIFAR-10, demonstrate that our method achieves better accuracy compared to existing adversarial training methods while maintaining strong robustness against attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09105 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples Mahdi, Soroush Amirmazlaghani, Maryam Saravani, Saeed Dehghanian, Zahra Machine Learning Artificial Intelligence In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance model robustness and accuracy without compromising performance on clean data. By using these examples across training epochs, MemLoss provides a balanced improvement in both natural accuracy and adversarial robustness. Experimental results on multiple datasets, including CIFAR-10, demonstrate that our method achieves better accuracy compared to existing adversarial training methods while maintaining strong robustness against attacks. |
| title | MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.09105 |