Search Results for author:
Found 6 papers, 1 papers with code
Adversarial Risk Bounds for Neural Networks through Sparsity based Compression
To study how robustness generalizes, recent works assume that the inputs have bounded $\ell_2$-norm in order to bound the adversarial risk for $\ell_\infty$ attacks with no explicit dimension dependence.
On the Trajectory of Stochastic Gradient Descent in the Information Plane
Studying the evolution of information theoretic quantities during Stochastic Gradient Descent (SGD) learning of Artificial Neural Networks (ANNs) has gained popularity in recent years.
On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks
In this work, this problem is studied through the lens of compression which is captured by the low-rank structure of weight matrices.
Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples
The framework can be used to propose novel attacks against learning algorithms for classification and regression tasks under various new constraints with closed form solutions in many instances.
On Generation of Adversarial Examples using Convex Programming
Moreover, this framework is capable of explaining various existing adversarial methods and can be used to derive new algorithms as well.
A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits
We carry out a tensor analysis on the expressive power inter-connections on convolutional arithmetic circuits (ConvACs) and relate our results to standard convolutional networks.
