Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks
The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In this paper, we seek to help alleviate this problem by systematizing the recent a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9663183/ |
| _version_ | 1828444204927287296 |
|---|---|
| author | Kaleel Mahmood Rigel Mahmood Ethan Rathbun Marten van Dijk |
| author_facet | Kaleel Mahmood Rigel Mahmood Ethan Rathbun Marten van Dijk |
| author_sort | Kaleel Mahmood |
| collection | DOAJ |
| description | The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In this paper, we seek to help alleviate this problem by systematizing the recent advances in adversarial machine learning black-box attacks since 2019. Our survey summarizes and categorizes 20 recent black-box attacks. We also present a new analysis for understanding the attack success rate with respect to the adversarial model used in each paper. Overall, our paper surveys a wide body of literature to highlight recent attack developments and organizes them into four attack categories: score based attacks, decision based attacks, transfer attacks and non-traditional attacks. Further, we provide a new mathematical framework to show exactly how attack results can fairly be compared. |
| first_indexed | 2024-12-10T21:41:06Z |
| format | Article |
| id | doaj.art-9664db0df05846048fb522573f1e9155 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T21:41:06Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9664db0df05846048fb522573f1e91552022-12-22T01:32:31ZengIEEEIEEE Access2169-35362022-01-0110998101910.1109/ACCESS.2021.31383389663183Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box AttacksKaleel Mahmood0https://orcid.org/0000-0002-7672-4449Rigel Mahmood1Ethan Rathbun2https://orcid.org/0000-0002-5437-2489Marten van Dijk3https://orcid.org/0000-0001-9388-8050Department of Computer Science and Engineering, University of Connecticut, Storrs, CT, USADepartment of Computer Science and Engineering, University of Connecticut, Storrs, CT, USADepartment of Computer Science and Engineering, University of Connecticut, Storrs, CT, USACWI Amsterdam, Amsterdam, XG, The NetherlandsThe field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In this paper, we seek to help alleviate this problem by systematizing the recent advances in adversarial machine learning black-box attacks since 2019. Our survey summarizes and categorizes 20 recent black-box attacks. We also present a new analysis for understanding the attack success rate with respect to the adversarial model used in each paper. Overall, our paper surveys a wide body of literature to highlight recent attack developments and organizes them into four attack categories: score based attacks, decision based attacks, transfer attacks and non-traditional attacks. Further, we provide a new mathematical framework to show exactly how attack results can fairly be compared.https://ieeexplore.ieee.org/document/9663183/Adversarial machine learningadversarial examplesadversarial defenseblack-box attacksecuritydeep learning |
| spellingShingle | Kaleel Mahmood Rigel Mahmood Ethan Rathbun Marten van Dijk Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks IEEE Access Adversarial machine learning adversarial examples adversarial defense black-box attack security deep learning |
| title | Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks |
| title_full | Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks |
| title_fullStr | Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks |
| title_full_unstemmed | Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks |
| title_short | Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks |
| title_sort | back in black a comparative evaluation of recent state of the art black box attacks |
| topic | Adversarial machine learning adversarial examples adversarial defense black-box attack security deep learning |
| url | https://ieeexplore.ieee.org/document/9663183/ |
| work_keys_str_mv | AT kaleelmahmood backinblackacomparativeevaluationofrecentstateoftheartblackboxattacks AT rigelmahmood backinblackacomparativeevaluationofrecentstateoftheartblackboxattacks AT ethanrathbun backinblackacomparativeevaluationofrecentstateoftheartblackboxattacks AT martenvandijk backinblackacomparativeevaluationofrecentstateoftheartblackboxattacks |