Search Results for author:
Found 4 papers, 0 papers with code
Polynomial Time Cryptanalytic Extraction of Neural Network Models
It resembles a differential chosen plaintext attack on a cryptosystem, which has a secret key embedded in its black-box implementation and requires a polynomial number of queries but an exponential amount of time (as a function of the number of neurons).
Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons
For example, we show how such a backdoored system can take any two images of a particular person and decide that they represent different persons (an anonymity attack), or take any two images of a particular pair of persons and decide that they represent the same person (a confusion attack), with almost no effect on the correctness of its decisions for other persons.
The Dimpled Manifold Model of Adversarial Examples in Machine Learning
We describe the results of numerous experiments which strongly support this new model, using both low dimensional synthetic datasets and high dimensional natural datasets.
A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance
The existence of adversarial examples in which an imperceptible change in the input can fool well trained neural networks was experimentally discovered by Szegedy et al in 2013, who called them "Intriguing properties of neural networks".
