Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers
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_ | 1866916211618480128 |
|---|---|
| author | Askarizadeh, Mohammad Javad Farahmand, Ebrahim Castro-Godinez, Jorge Mahani, Ali Cabrera-Quiros, Laura Salazar-Garcia, Carlos |
| author_facet | Askarizadeh, Mohammad Javad Farahmand, Ebrahim Castro-Godinez, Jorge Mahani, Ali Cabrera-Quiros, Laura Salazar-Garcia, Carlos |
| contents | Deep Neural Networks (DNNs) have advanced in many real-world applications, such as healthcare and autonomous driving. However, their high computational complexity and vulnerability to adversarial attacks are ongoing challenges. In this letter, approximate multipliers are used to explore DNN robustness improvement against adversarial attacks. By uniformly replacing accurate multipliers for state-of-the-art approximate ones in DNN layer models, we explore the DNNs robustness against various adversarial attacks in a feasible time. Results show up to 7% accuracy drop due to approximations when no attack is present while improving robust accuracy up to 10% when attacks applied. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11665 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers Askarizadeh, Mohammad Javad Farahmand, Ebrahim Castro-Godinez, Jorge Mahani, Ali Cabrera-Quiros, Laura Salazar-Garcia, Carlos Machine Learning Cryptography and Security Deep Neural Networks (DNNs) have advanced in many real-world applications, such as healthcare and autonomous driving. However, their high computational complexity and vulnerability to adversarial attacks are ongoing challenges. In this letter, approximate multipliers are used to explore DNN robustness improvement against adversarial attacks. By uniformly replacing accurate multipliers for state-of-the-art approximate ones in DNN layer models, we explore the DNNs robustness against various adversarial attacks in a feasible time. Results show up to 7% accuracy drop due to approximations when no attack is present while improving robust accuracy up to 10% when attacks applied. |
| title | Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2404.11665 |