75 citations · 280 across the 41 of their papers we have counts for
Showing 2020Show all
3 papers · 1 filter
cs.LG2020★ 3 cited
Detecting Trojaned DNNs Using Counterfactual Attributions
Karan Sikka, Indranil Sur, Susmit Jha +2
We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with…
cs.RO2020★ 15 cited
Learning Certified Control using Contraction Metric
Dawei Sun, Susmit Jha, Chuchu Fan
In this paper, we solve the problem of finding a certified control policy that drives a robot from any given initial state and under any bounded disturbance to the desired referenc…
cs.LG2020★ 1 cited
An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz +4
Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model.…