Search Results for author:
Found 7 papers, 2 papers with code
Efficient Symbolic Reasoning for Neural-Network Verification
They allow us to encode many verification problems for neural networks as quadratic programs.
Learning Optimal Conformal Classifiers
However, using CP as a separate processing step after training prevents the underlying model from adapting to the prediction of confidence sets.
Towards transformation-resilient provenance detection of digital media
In this paper, we introduce ReSWAT (Resilient Signal Watermarking via Adversarial Training), a framework for learning transformation-resilient watermark detectors that are able to detect a watermark even after a signal has been through several post-processing transformations.
An efficient nonconvex reformulation of stagewise convex optimization problems
We establish theoretical properties of the nonconvex formulation, showing that it is (almost) free of spurious local minima and has the same global optimum as the convex problem.
Verification of Non-Linear Specifications for Neural Networks
We show that a number of important properties of interest can be modeled within this class, including conservation of energy in a learned dynamics model of a physical system; semantic consistency of a classifier's output labels under adversarial perturbations and bounding errors in a system that predicts the summation of handwritten digits.
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
We demonstrate this is an issue for current agents, where even matching the compute used for training is sometimes insufficient for evaluation.
A Dual Approach to Scalable Verification of Deep Networks
In contrast, our framework applies to a general class of activation functions and specifications on neural network inputs and outputs.
