Breaking Certified Defenses: Semantic Adversarial Examples With Spoofed Robustness Certificates: Difference between revisions
Jump to navigation
Jump to search
(Created page with " == Presented By == Gaurav Sikri == Background == Adversarial examples are inputs to machine learning or deep neural network models that an attacker intentionally designs to...") |
No edit summary |
||
Line 5: | Line 5: | ||
== Background == | == Background == | ||
Adversarial examples are inputs to machine learning or deep neural network models that an attacker intentionally designs to deceive the model or to cause the model to make a wrong prediction. This is done by adding a little noise to the original image or perturbing an original image and creating an image that is not identified by the network and the model misclassifies the new image. | Adversarial examples are inputs to machine learning or deep neural network models that an attacker intentionally designs to deceive the model or to cause the model to make a wrong prediction. This is done by adding a little noise to the original image or perturbing an original image and creating an image that is not identified by the network and the model misclassifies the new image. | ||
[[File:adversarial_example.png|500px|Image: 500 pixels]] |
Revision as of 20:30, 8 November 2020
Presented By
Gaurav Sikri
Background
Adversarial examples are inputs to machine learning or deep neural network models that an attacker intentionally designs to deceive the model or to cause the model to make a wrong prediction. This is done by adding a little noise to the original image or perturbing an original image and creating an image that is not identified by the network and the model misclassifies the new image.