2 papers
stat.ML2020
Stochastic Linear Bandits Robust to Adversarial Attacks
Ilija Bogunovic, Arpan Losalka, Andreas Krause +1
We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget (i.e., an up…
cs.LG2018
Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders
Partha Ghosh, Arpan Losalka, Michael J Black
Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen li…