22 citations · 44 across the 18 of their papers we have counts for
3 papers · 1 filter
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Gaurang Sriramanan, Sravanti Addepalli, Arya Baburaj +1
Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable e…
Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks
Sravanti Addepalli, Dipesh Tamboli, R. Venkatesh Babu +1
In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct…
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
Sravanti Addepalli, Vivek B. S., Arya Baburaj +2
As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to…