91 citations · 174 across the 10 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.CV2017★ 91 cited
UPSET and ANGRI : Breaking High Performance Image Classifiers
Sayantan Sarkar, Ankan Bansal, Upal Mahbub +1
In this paper, targeted fooling of high performance image classifiers is achieved by developing two novel attack methods. The first method generates universal perturbations for tar…
cs.CV2017
The Do's and Don'ts for CNN-based Face Verification
Ankan Bansal, Carlos Castillo, Rajeev Ranjan +1
While the research community appears to have developed a consensus on the methods of acquiring annotated data, design and training of CNNs, many questions still remain to be answer…