Difference between revisions of "One pixel attack for fooling deep neural networks"

From statwiki
Jump to: navigation, search
(Methodology)
Line 11: Line 11:
  
  
= Methodology =
 
  
 +
= Methodology =
 +
 +
We first formalize the generation of adversarial images as an constrained optimization problem.
 +
Let $f_t$
  
 
= Evaluation and Results =
 
= Evaluation and Results =

Revision as of 21:47, 25 March 2018

Presented by

1. Ziheng Chu

2. Minghao Lu

3. Qi Mai

4. Qici Tan

Introduction

Methodology

We first formalize the generation of adversarial images as an constrained optimization problem. Let $f_t$

Evaluation and Results

Measurement Metrics and Datasets

Results

Discussion and Future Work