FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

IDRL

Last update: Dec 15, 2022

Overview

FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

Case study of the FCA. The code can be find in FCA.

Cases of Digital Attack

Carmear distance is 3

before
after

Carmear distance is 5

before
after

Carmear distance is 10

before
after

Cases of Multi-view Attack

before
after

The first row is the original detection result. The second row is the camouflaged detection result.

before
after

The first row is the original detection result. The second row is the camouflaged detection result.

Ablation study

Different combination of loss terms

As we can see from the Figure, different loss terms plays different roles in attacking. For example, the camouflaged car generated by obj+smooth (we omit the smooth loss, and denotes as obj) can hidden the vehicle successfully, while the camouflaged car generated by iou can successfully suppress the detecting bounding box of the car region, and finally the camouflaged car generated by cls successfully make the detector to misclassify the car to anther category.

Different initialization ways

original	basic initialization	random initialization	zero initialization

You might also like...

Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

Min-Max Adversarial Attacks [Paper] [arXiv] [Video] [Slide] Adversarial Attack Generation Empowered by Min-Max Optimization Jingkang Wang, Tianyun Zha

12 Nov 23, 2022

Super Pix Adv - Offical implemention of Robust Superpixel-Guided Attentional Adversarial Attack (CVPR2020)

Super_Pix_Adv Offical implemention of Robust Superpixel-Guided Attentional Adver

8 Oct 26, 2022

Code for the CVPR2022 paper "Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity"

Introduction This is an official release of the paper "Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity" (arxiv link). Abstrac

21 Nov 23, 2022

Official Pytorch implementation of ICLR 2018 paper Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge.

Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge: Official Pytorch implementation of ICLR 2018 paper Deep Learning for Phy

47 Nov 6, 2022

A PyTorch implementation of Radio Transformer Networks from the paper "An Introduction to Deep Learning for the Physical Layer".

An Introduction to Deep Learning for the Physical Layer An usable PyTorch implementation of the noisy autoencoder infrastructure in the paper "An Intr

120 Nov 21, 2022

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network An official PyTorch implementation of the RBSRICNN network as desc

6 Nov 14, 2022

Out-of-boundary View Synthesis towards Full-frame Video Stabilization

Comments

How to use "phy_attack" dataset

Hello, I found that the default dataset used in your code is "phy_attack" which is the same one used in DAS. But I don't know how to set other directories such as "train_new", "train_label_new", etc. Could you give me more detailed guidelines for using the dataset?

I'd really appreciate it if you reply to my question. Thank you.

opened by pianoforte23 16
attack performance

Are there some tricks that can effectively improve the attack performance? My attack performance is not high after training, only about 70%, and it is worse for small objects. Thank you~

opened by FenHua 0
How to extract the texture ?

Hello, thanks for the great work. I am wondering how we can extract the generated attack texture to use it on other 3D software or print it for the real world? Is it possible for us to save the texture as an image file? Because we found that the output texture is saved as a NumPy file, which can only be used for this neural renderer code.

Thank you.

opened by naufalso 1

FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

Related tags

Overview

FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

Cases of Digital Attack

Carmear distance is 3

Carmear distance is 5

Carmear distance is 10

Cases of Multi-view Attack

Ablation study

Different combination of loss terms

Different initialization ways

You might also like...

Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

Super Pix Adv - Offical implemention of Robust Superpixel-Guided Attentional Adversarial Attack (CVPR2020)

Code for the CVPR2022 paper "Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity"

Official Pytorch implementation of ICLR 2018 paper Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge.

A PyTorch implementation of Radio Transformer Networks from the paper "An Introduction to Deep Learning for the Physical Layer".

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

Out-of-boundary View Synthesis towards Full-frame Video Stabilization

Multi-Scale Geometric Consistency Guided Multi-View Stereo

Code for "Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo"

Comments

How to use "phy_attack" dataset

attack performance

How to extract the texture ?

Owner

IDRL

(CVPR 2022 - oral) Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry

POPPY (Physical Optics Propagation in Python) is a Python package that simulates physical optical propagation including diffraction

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

Blender add-on: Add to Cameras menu: View → Camera, View → Add Camera, Camera → View, Previous Camera, Next Camera

Causal-Adversarial-Instruments - PyTorch Implementation for Developing Library of Investigating Adversarial Examples on A Causal View by Instruments

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones Code

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)

Full body anonymization - Realistic Full-Body Anonymization with Surface-Guided GANs

Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021

This is the official code for the paper "Ad2Attack: Adaptive Adversarial Attack for Real-Time UAV Tracking".