Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Perception Deception - Physical Adversarial Attack Challenges

Black Hat via YouTube

Overview

Limited-Time Offer: Up to 75% Off Coursera Plus!
7000+ certificate courses from Google, Microsoft, IBM, and many more.
This course focuses on physical adversarial attack challenges in the context of object detection using YOLOv3. The learning outcomes include understanding the fundamentals of object detection, exploring adversarial examples and their impact on deep neural networks, and implementing physical white box attacks against YOLOv3. The course teaches skills such as constructing differentiable input patches, managing color with non-printability loss, and optimizing attacks for various distances and angles. The teaching method involves a presentation with examples and a deep dive into YOLOv3. The intended audience for this course includes individuals interested in cybersecurity, machine learning, and computer vision.

Syllabus

Intro
Car Safety - Unintended Acceleration
Car Perception While Driving
Behind Perception: End2End Object Detection
State-of-the-Art Vision-based Object Detection
Current Status of Adversarial Example
Adversarial Examples & L2 Norm Perturbations Impact to DNN
Explore Chances of Physical White Box Attack against YOLOV3
Deep Dive into YOLOv3
Training Dataset - MS COCO Dataset
YOLOv3 Prediction
Threat Model : Physical Image Patch Attack
Our Physical Attack Approach & Objectives
Differentiable Input Patch Construction
Attack Objective 1 - Object Fabrication
Attack Objective 2 - Object Vanishing
Challenges to the Success of Physical Attack
Tactics to the Challenges
Color Management with Non-Printability Loss
RT + TV for Various Distances & Angles
Put Everything Together: An Iterative Optimization
Conclusion & Takeaway

Taught by

Black Hat

Reviews

Start your review of Perception Deception - Physical Adversarial Attack Challenges

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.