Search Results for author:
Found 7 papers, 1 papers with code
An Information-Theoretic Explanation for the Adversarial Fragility of AI Classifiers
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.
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
In this paper, we present a simple hypothesis about a feature 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.
Globally Optimal Segmentation of Mutually Interacting Surfaces using Deep Learning
In this work, we propose to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters.
Dual camera snapshot hyperspectral imaging system via physics informed learning
Various methods using CNNs have been developed in recent years to reconstruct HSIs, but most of the supervised deep learning methods aimed to fit a brute-force mapping relationship between the captured compressed image and standard HSIs.
A deep learning network with differentiable dynamic programming for retina OCT surface segmentation
Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for DL networks to learn the global structure of the target surfaces, including surface smoothness.
gcDLSeg: Integrating Graph-cut into Deep Learning for Binary Semantic Segmentation
To combine the strengths of both approaches, we propose in this study to integrate the graph-cut approach into a deep learning network for end-to-end learning.
Distance Guided Generative Adversarial Network for Explainable Binary Classifications
Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification.
