output
20042021
most citedDetecting Adversarial Samples from Artifacts

366 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2018★ 7 cited

Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning

Jasjeet Dhaliwal, Saurabh Shintre

Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network. This vulnerability can lead to potentially harmful consequenc…

cs.CV2018★ 291 cited

Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches

Sarfaraz Hussein, Pujan Kandel, Candice W. Bolan +2

Risk stratification (characterization) of tumors from radiology images can be more accurate and faster with computer-aided diagnosis (CAD) tools. Tumor characterization through suc…