| Title | A delayed Elastic-Net approach for performing adversarial attacks |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Cancela, Brais, Bolón-Canedo, Verónica, Alonso-Betanzos, Amparo |
| Conference Name | 2020 25th International Conference on Pattern Recognition (ICPR) |
| Keywords | Benchmark testing, Data preprocessing, Measurement, Measurement and Metrics Testing, Metrics, Pattern recognition, Perturbation methods, pubcrawl, Robustness, security, Size measurement |
| Abstract | With the rise of the so-called Adversarial Attacks, there is an increased concern on model security. In this paper we present two different contributions: novel measures of robustness (based on adversarial attacks) and a novel adversarial attack. The key idea behind these metrics is to obtain a measure that could compare different architectures, with independence of how the input is preprocessed (robustness against different input sizes and value ranges). To do so, a novel adversarial attack is presented, performing a delayed elastic-net adversarial attack (constraints are only used whenever a successful adversarial attack is obtained). Experimental results show that our approach obtains state-of-the-art adversarial samples, in terms of minimal perturbation distance. Finally, a benchmark of ImageNet pretrained models is used to conduct experiments aiming to shed some light about which model should be selected whenever security is a role factor. |
| DOI | 10.1109/ICPR48806.2021.9413170 |
| Citation Key | cancela_delayed_2021 |
A delayed Elastic-Net approach for performing adversarial attacks