no code implementations • 27 Jan 2019 • Hui Xie, Jirong Yi, Weiyu Xu, Raghu Mudumbai
We present a simple hypothesis about a compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations.
no code implementations • 26 Mar 2020 • Zain Khan, Jirong Yi, Raghu Mudumbai, Xiaodong Wu, Weiyu Xu
Recent works have demonstrated the existence of {\it adversarial examples} targeting a single machine learning system.
no code implementations • 28 Jul 2020 • Jirong Yi, Raghu Mudumbai, Weiyu Xu
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the label of interest.
no code implementations • 5 Aug 2020 • Jirong Yi, Myung Cho, Xiaodong Wu, Raghu Mudumbai, Weiyu Xu
In this paper, we consider the problem of designing optimal pooling matrix for group testing (for example, for COVID-19 virus testing) with the constraint that no more than $r>0$ samples can be pooled together, which we call "dilution constraint".
no code implementations • 27 Sep 2023 • Eva Riherd, Raghu Mudumbai, Weiyu Xu
We propose a general method for semantic representation of images and other data using progressive coding.