TY - GEN
T1 - Explainability of Image Classifiers for Targeted Adversarial Attack
AU - Pandya, Mayur Anand
AU - Siddalingaswamy, P. C.
AU - Singh, Sanjay
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Deep neural networks outperform their contemporary peer models for computer vision tasks. These models are complex and challenging to interpret for practitioners. As more and more learning algorithms are deployed in real-world applications, model interpretability has become quite essential. Incidentally, Model interpretability is quite relevant to the case of deep neural networks as they can fall prey to adversarial attacks crafted by adversaries. In this paper, we launch an iterative targeted attack using a set of image classes on base architectures and interpret the results by applying an explanation algorithm before and after the attack. This process leads us to some valuable conclusions regarding the effects of the attack on the explanation methods and how explanation methods can be made to have more adversarial robustness.
AB - Deep neural networks outperform their contemporary peer models for computer vision tasks. These models are complex and challenging to interpret for practitioners. As more and more learning algorithms are deployed in real-world applications, model interpretability has become quite essential. Incidentally, Model interpretability is quite relevant to the case of deep neural networks as they can fall prey to adversarial attacks crafted by adversaries. In this paper, we launch an iterative targeted attack using a set of image classes on base architectures and interpret the results by applying an explanation algorithm before and after the attack. This process leads us to some valuable conclusions regarding the effects of the attack on the explanation methods and how explanation methods can be made to have more adversarial robustness.
UR - http://www.scopus.com/inward/record.url?scp=85149229436&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149229436&partnerID=8YFLogxK
U2 - 10.1109/INDICON56171.2022.10039871
DO - 10.1109/INDICON56171.2022.10039871
M3 - Conference contribution
AN - SCOPUS:85149229436
T3 - INDICON 2022 - 2022 IEEE 19th India Council International Conference
BT - INDICON 2022 - 2022 IEEE 19th India Council International Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th IEEE India Council International Conference, INDICON 2022
Y2 - 24 November 2022 through 26 November 2022
ER -